UA126555C2 - Generating digital models of crop yield based on crop planting dates and relative maturity values - Google Patents

Abstract

A method for generating digital models of potential crop yield based on planting date, relative maturity, and actual production history is provided. In an embodiment, data representing historical planting dates, relative maturity values, and crop yield is received by an agricultural intelligence computer system. Based on the historical data, the system generates spatial and temporal maps of planting dates, relative maturity, and actual production history. Using the maps, the system creates a model of potential yield that is dependent on planting date and relative maturity. The system may then receive actual production history data for a particular field. Using the received actual production history data, a particular planting date, and a particular relative maturity value, the agricultural intelligence computer system computes a potential yield for a particular field.

Description

receiving, via a network on a server computer system, third electronic digital data containing a plurality of values that reflect actual yield values for a crop planted in a plurality of fields for a plurality of years; generating, using digitally programmed potential yield modeling instructions on the server computer system, one or more maps of actual yield values from the plurality of values representing actual yield values for the corresponding location are generated using digitally programmed potential yield modeling instructions on the server computer system , a planting date and relative maturity potential yield model based, at least in part, on one or more relative maturity maps, one or more planting date maps, and one or more actual yield maps, the potential yield model being based, at least in part, on on the location of prognostic variables and on the time-sensitive covariance matrix of prognostic variables; receiving, via a network on a server computer system, fourth electronic digital data containing a plurality of values that reflect actual yield values for a particular field; calculate, using digital programmed yield estimation instructions on a server computer system, by means of a potential yield model, a specific potential yield for a specific field based, at least in part, on a plurality of values representing actual yield values for a specific field; generate one or more planting date recommendations or seed type recommendations based, at least in part, on input from the crop potential yield model; generate one or more application controller scripts based on one or more planting date recommendations or seed type recommendations; sending one or more scripts to the application controller, wherein the application controller executes the one or more scripts to cause the application controller to control the operating parameters of the agricultural equipment. «r Mr shk Sh she rent i ti 106 1yuYu Kotova and pAA-5 BZh- Field | Outer selves

Kumam uter | Sitsskogospacharsky Z kava yapistriy ke 4315 Vidlalevy | | PA Kozheriler application thanks to te 109 Network E) Sho lori, rt 135 Communication level ra a and x 136 non-destructive from melezhvovannia dutetnoi r: ! 135 Tvozruyuyh from the educational index | | not tn KVN | Such data! t ty t KO sSzhovtsche -k LAZ instructions on gin yield assessment 138 Presentation level 140 Data management tools.

TO The level of ayairat provision of verkalization

OO

KM Sil ezhhogospalareka intellectual chv vichislvalya siste

Fig. 1

COPYRIGHT NOTICE

YOOOO1| Part of this description of the patent document contains materials subject to copyright protection. The copyright owner does not object to the facsimile reproduction by anyone of the patent document or description of the patent as it appears from the patent file or patent registration of the Patent and Trademark Office, and otherwise retains all copyright or rights. There is 2015 Tne S Iitaie Sogrogaiiop.

TECHNICAL FIELD

I0002| The present invention relates to digital computer modeling of the potential yield of an agricultural crop based on planting dates and corresponding ripening indicators. Additionally, the present invention relates to the generation of messages, recommendations, and a graphical user interface based on digital models of potential yield.

TECHNICAL LEVEL

0003) The approaches outlined in this section are approaches that need to be implemented, but not necessarily, approaches that have been developed or implemented previously. Thus, unless otherwise indicated, it should not be assumed that any approaches described in this section are prior art solely because they are included in this section.

І0004| Typically, farmers are forced to make planting decisions for one or more fields based on incomplete information. More specifically, before planting a crop, the farmer must determine when to plant the crop to achieve maximum crop yield. Although the general planting season for a particular crop is generally known, due to changes in temperature and weather-related factors, the current yield of the crop may vary depending on the planting date during the planting season. 0005) An additional decision that the farmer must make is the selection of the type of hybrid seed to plant. Agricultural crops, such as corn, usually have numerous types of hybrids, each of which can produce different corn yields. In addition to the fact that the type of hybrid affects the overall yield of an agricultural crop, the choice of one seed among others varies depending on the date of planting and location. For example, for a particular planting date at a first location, a first type of seed may provide a higher yield compared to a second type of seed, while for such a planting date at a second location, a second type of seed may provide a higher yield compared to the first type of seed.

I0006| Given the dependence of total yield on the type of seed to be planted, the date of planting the seed and the location of the field, objective data determining the best planting date and type of seed are usually not available. Since the type of seed to plant and the date of planting have a significant impact on the overall yield of the farm and. thus, to the farmer's overall profit, it would be beneficial to provide the farmer with data indicating the best planting date and seed selection for a particular farmer's field.

BRIEF DESCRIPTION OF THE ESSENCE OF THE INVENTION

I0007| The attached formula of the invention can serve as a brief description of the essence of the invention.

BRIEF DESCRIPTION OF GRAPHIC MATERIALS

I0O008) On graphic materials:

II0009| Fig. 1 illustrates an example of a computing system designed to perform the functions described herein and illustrated in the field with other devices with which the system may interact. 0010) Fig. 2 illustrates two displays of an example logical organization of instruction sets in main memory when loading an example mobile application for execution. 0011) Fig. C illustrates a programmed process by which an agricultural intelligent computing system generates one or more pre-configured agronomic models using agronomic data provided by one or more data sources. 00121 Fig. 4 is a functional diagram illustrating a computer system 400 on which an embodiment of the invention may be implemented. 0013) Fig. 5 illustrates an example of an implementation of a screen display in the timeline mode for input data. 0014) Fig. 6 illustrates an example of a variant of the implementation of the screen display in the digital table mode for the entered data. because ИО0О15| Fig. 7 illustrates an example of a method for creating and using a digital model of crop potential yield based on planting date and relative maturity. 0016) Fig. 8 illustrates an example of a variant in the stages of corn development.

ИО0О17| Fig. 9 illustrates an example of a table where the number of growing stage days is used to determine the beginning and end of different phenological stages of development.

DETAILED DESCRIPTION OF THE ESSENCE OF THE INVENTION

ІІ0018| In the following description, for the sake of clarity, numerous specific details are set forth to provide a complete understanding of the present invention. Nevertheless, it is clear that embodiments of the invention can be implemented in practice without these characteristic details.

In other cases, well-known structures and devices are illustrated in the form of a functional diagram to avoid overcomplicating this description. The options for implementing the invention are outlined in this section according to the following plan: 1. GENERAL OVERVIEW 2. EXAMPLE OF AGRICULTURAL INTELLECTUAL COMPUTING

SYSTEMS

21. OVERVIEW OF THE STRUCTURE 2.2. APPLICATION PROGRAM OVERVIEW 2-3. DATA ENTRY INTO THE COMPUTER SYSTEM 2.4. OVERVIEW OF THE PROCESS - PREPARATION OF THE AGRONOMIC MODEL 2.5. IMPLEMENTATION EXAMPLE - HARDWARE OVERVIEW 3. YIELD ASSESSMENT MODEL 3.1. RECEIVED DATA 3.2.1 GENERATION OF RETROSPECTIVE MAPS 3.3. SIMULATION OF POTENTIAL YIELD 3.4. SIMULATION OF PREDICTED YIELD 3.5. AGRICULTURAL STRESS INDICES 3.5. and PHENOLOGY OF AGRICULTURAL CULTURE 3.5.2. STRESS FROM FLOODING 3.5.3. STRESS FROM DROUGHT

From 3.5.4. INITIAL STRESS FROM DROUGHT 3.5.5. DAYTIME THERMAL SIRES 3.5.6. NIGHT HEAT STRESS 3.5.7. STRESS. CAUSED BY THE USE OF BIOGENIC SUBSTANCES 3.6. MODELS. STRENGTHENING 4. USE MODEL 4.1. ASSESSMENT OF THE GENERAL YIELD OF AGRICULTURAL CULTURE 4.2. RECOMMENDATIONS REGARDING PLANTING DATE 4.3. SEED RECOMMENDATIONS 5. ADVANTAGES OF CERTAIN EMBODIMENTS OF THE INVENTION 6. ADDITIONAL AND ALTERNATIVES 0019) K GENERAL OVERVIEW (0020) Aspects of the present invention relate principally to computer-implemented technologies for generating a model-based crop yield estimation model potential yield based on planting date, relative maturity and actual yield for one or more fields. In an embodiment of the invention, the agricultural intelligent computing system receives retrospective data that determines the planting dates of the agricultural crop, relative seed maturity values, and previous yield data for multiple locations. Based on the received retrospective data, the system creates one or more maps of planting dates, relative ripening and actual yield indicators. Using the generated maps, the system generates a model of potential yield that depends on relative maturity, planting dates and actual yield figures. The system then obtains the actual yield values for a particular field. Using the actual yield figures for a particular field, a particular planting date and a particular relative maturity value, the system calculates the potential yield for a particular field. The system can then model the current yield of the crop based on the calculated potential yield. 00211 In an embodiment of the invention, the method comprises receiving, over a network, on a server computer system containing one or more processors and a digital memory, first electronic digital data containing a plurality of values representing retrospective 60 data on the relative maturity of an agricultural crop , planted in a plurality of fields for a plurality of years: generating one or more relative maturity maps from the plurality of values representing retrospective relative maturity using potential yield modeling instructions for digital programmable logic of the server computer system; receiving, via a network on a server computer system, second electronic digital data comprising a plurality of values comprising retrospective planting dates for a crop planted in a plurality of fields over a plurality of years; generating one or more relative maturity maps from the plurality of values representing the retrospective planting date using potential yield modeling instructions for the digital programmable logic of the server computer system; receiving via a network on a server computer system third electronic digital data containing actual yield indicators for an agricultural crop planted in a plurality of fields for a plurality of years; generating one or more maps from the plurality of values representing actual yield values using the potential yield modeling instructions for the digital programmable logic of the server computer system; generating a potential yield model dependent on planting date and relative maturity based, at least in part, on one or more relative maturity maps, one or more planting date maps, and one or more actual yield maps using potential yield modeling instructions for digital programmable logic server computer system; receiving via the network on the server computer system fourth electronic digital data containing a plurality of values reflecting actual yield indicators for a certain field; computing from the potential yield model a specific potential yield for a specific field based, at least in part, on a plurality of values representing actual yield values for the specific field using potential yield modeling instructions for digital programmable logic of the server computer system. 0022) 2. EXAMPLE OF AGRICULTURAL INTELLECTUAL COMPUTING

SYSTEMS

(0023) 2.11 STRUCTURE OVERVIEW

I0024| Fig. 1 illustrates an example of a computing system implemented with the capability

To perform the functions described in this document and illustrated in the field with other devices with which the system can interact. In an embodiment of the invention, the user 102 owns, operates, or possesses the field control computing device 104 at a field location, or associated with a field location, such as an agricultural field, or at a location where one or more agricultural fields. Field controller computing device 104 is programmed or configured to provide field data 106 to agricultural intelligent computing system 130 via one or more networks 109 .

I0025| Examples of field data 106 include (a) identifying data (eg, field area in acres, field name, field identifiers, geographic identifiers, boundary identifiers, crop identifiers, and any other relevant data that can be used to identify farm land for example, public land unit (PLU), lot and block number, parcel number, geographic coordinates and boundaries, farm serial number (FAR), farm number, lot number, field number, 640-acre field, 36-square-mile field , and/or extent, (B) harvest data (e.g., type of crop, crop varieties, crop rotation, whether crops were grown organically, date of harvest, actual yield rates (APR), target yield, yield, cost of planting, income from the harvest, grain moisture, methods of mechanical processing, information on previous weather conditions), (c) data on the soil (for example, type, composition, pH, organic matter (OM), cation exchange capacity (ECC), (4) data on planting (e.g. date of planting, type of cereal, relative development (CM) of planted cereal, planting density), (ee) data on fertilizers (e.g., type of fertilizer (nitrogen containing phosphorus, potassium), type of application, date of application, quantity , source, method), (І) data on pesticides and, for example, pesticides, herbicides, fungicides, OTHER substances or mixtures of substances THAT are used in

QUALITIES of growth regulators, defoliant or desiccant, date of application, amount, source, method), (du) irrigation data (e.g., date of application, volume, source, method), (n) weather conditions (e.g., rainfall, temperature , wind, pressure, visibility, cloudiness, heat index, dew point, humidity, snow depth, air quality, sunrise, sunset), (i) image data (eg image information and light spectrum From 60 agricultural device, sensor, camera, computer, smartphone, PDA, unmanned aerial vehicle, airplane or satellite), () reconnaissance observations (photos, videos, free-form recordings, voice recordings, decoding of recordings, weather conditions (temperature, precipitation (current and over a period of time), soil moisture, crop growth phase, wind speed, relative humidity, dew point, black layer)), and (soil, seed, crop phenology, pest and disease report, and forecast sources and databases .

I0026| The external data server computer 108 is functionally connected to the agricultural intelligent computing system 130 and is programmed or implemented to send external data 110 to the agricultural intelligent computing system 30 via network(s) 109. The external data server computer 108 may be proprietary , or may be staffed by the same legal entity or entity operating the agricultural intelligent computing system 130 or by different entities or entities, such as a government agency, non-governmental organization (NGO), ha/or private vendor data transmission services. Examples of external data include weather data, image data, soil data or, among other things, statistical data related to crop yields. The external data 110 may contain the same types of information as the field data 106. In some embodiments of the invention, the external data 110 provided by the computer to the external data server 108 belong to the same objects that are owned and/or be processed with the agricultural intelligent computing system /- 130. For example, the agricultural intelligent computing system 130 may include a data server that focuses on a type of data, such as weather data, that may otherwise be provided by third-party sources. In some embodiments of the invention, the external data server computer 108 may actually be embedded in the system 130.

I0027| Agricultural devices 111 may have one or more remote sensors 112 mounted thereon. while these sensors are connected with the ability to exchange data, both directly and indirectly, through the agricultural devices 111, with the agricultural intelligent computing system 130, and are programmed or made with the ability to send sensor data to the agricultural intelligent computing system 130. Examples of agricultural devices 111 include factors, combines, harvesters, planters, trucks, fertilizer application equipment, unmanned aerial vehicles and any other units of physical mechanisms or hardware, usually mobile mechanisms, and which can be used in tasks related to with agriculture. In some embodiments of the invention, one unit of the device 111 may contain a plurality of sensors 112 connected locally in a network of devices; local network of controllers (LAN) is an example of such a network that can be installed on combines or harvesters. The application controller 114 is communicable (with the agricultural intelligent computing system 130 via the network(s) 109, and is programmed or implemented to receive from the agricultural intelligent computing system 130 one or more scripts to control the operational parameters of the agricultural vehicle, or their For example, the LAN bus interface of the CAM controllers can be used to exchange data between the agricultural intelligent computing system 130 and the agricultural devices 111, for example, as used in

SIIMATE RIEGOMIEMU OVIME, which is available from Te Siyitaiye Sogrogaiiop, San-

Francisco, California. Sensor data may contain the same types of information as field data 106. (0028) Devices 111 may include a cockpit computer 115 that includes a cockpit application that may include a version or example of a mobile application for device 104 that is further described. in other sections of this document. In an embodiment of the invention, the cabin computer 115 includes a portable computer, most often a computer the size of a tablet or smartphone, with a color graphic screen installed inside the operator's cabin of the device 111.

The cab computer 115 may implement some or all of the operations and functions described further herein with respect to the field controller computing device 104.

I0029| Network(s) 109 is broadly any combination of one or more communication networks, including local area networks, wide area networks, or a network

Internet, using wired or wireless communication channels, including terrestrial or satellite communication channels. The network () can be implemented using any data transmission medium or mechanism provided for data exchange between the various bo elements in Fig. 1. Various elements in Fig. 1 can have direct (wired or wireless)

communication channels. Each of the sensors 112, the controller 114, the external data server computer 108, and other elements of the system includes an interface compatible with the network(s) 109 and is programmed or implemented to enable the use of standard protocols for exchanging data over the network, for example, TCP/ IR, Winoyoy, SAM, and high-level protocols, for example, NITR, TI 5 and the like.

I0030| The agricultural intelligent computing system 130 is programmed or configured to receive field data 106 from the field control computing device 104, external data 110, from the external data server computer 108, and sensor data from remote sensors 112. The agricultural intelligent computing system 130 may additionally be made capable of hosting, using or executing one or more computer programs, other software elements, digital programmable logic, for example. ERA or ABIS. or any combination thereof to perform translation and storage of data elements, construct digital models of one or more crops in one or more fields, generate recommendations and messages, and generate and send scripts to the application controller 114, in ways further described elsewhere herein description

I0O31) In an embodiment of the invention, the agricultural intelligent computing system 130 is programmed with or includes a communication layer 132, a presentation layer 134, a data management layer 140, a hardware/virtualization layer 150, and a storage of models and field data 160. In the context of this document, the term " layer" means a combination of digital interface electronics, microcontrollers, embedded software and/or computer programs, or other software elements. (00321) The communication layer 132 may be programmed or implemented to perform input/output interface functions, including sending requests to the field controller computing device 104, the external data server computer 108, and the remote sensors 112 to receive field data, external data, and sensor data, respectively. The communication layer 132 may be programmed or implemented to send the received data to the model and field data store 160 for storage as field data 106 .

From 00331 The presentation layer 134 may be programmed or implemented to generate a graphical user interface (GUI) for display on the field controller's computing device 104, the cab computer 115, or other computers that are connected to the system 130 via the network 109. may include controls for the input data to enter into the agricultural intelligent computing system 1 30, generate model queries and/or recommendations. and/or displaying recommendations, messages, models, and other field data.

Y0034| Data management layer 140 may be programmed or implemented to manage read and write operations using storage 160 and other system functionality, including query and result sets passed between system functionality and storage. Examples of the data management layer 140 include, among other things, the interface code of CHUOVS, BOI servers, and/or the interface code of the NABOOR. The repository 160 may contain a database. In the context of this document, the term "database" means both an array of data and a relational database management system (RDBMS5), or both.In the context of this document, a database may contain any set of data, including a hierarchical database, a relational database, a flat file database, an object-relational database data, an object-oriented database, and any other structured set of records or data stored in a computer system.

Examples of KOVM5 include, among other things, the OKASIEF, MUBOY, IVMF 082 databases,

MISKOBOGTO 50 5EKMEK.

BO ZUVABEF and ROBTOVEZ5OYI.. However, any database that allows the systems and methods described in this document can be used.

И0О35| If the field data 106 is not directly inputted to the agricultural intelligent computing system by one or more agricultural machines or agricultural machine devices interacting with the agricultural intelligent computing system, the user may be prompted to enter such information through one or more user interfaces on the device user (which is served by the agricultural intelligent computing system). In the embodiment of the invention given as an example, the user can specify identification data by accessing the map on the user's device (which is served by the agricultural intelligent computing system) and select a certain CI, which is graphically displayed on the map. In an alternative embodiment of the invention, the user 102 can specify identification data by accessing a map on the user's device (which is served by the agricultural intelligent computing system 130) by drawing the plot boundaries on top of the map. This choice of SI O or drawing on the map reflects geographic identifiers. In an alternative embodiment of the invention, the user may provide identification data by accessing identification field data (provided as vector files or similar format) from the US Department of Agriculture's Farm Service Administration or another source, using the user's device, and provide such identifying field data to the agricultural intelligent computing system.

ИЙ0О3б| In an exemplary embodiment of the invention, the agricultural intelligent computing system 130 is programmed to generate and display a graphical user interface, . containing a data manager for entering data. Once one or more fields have been identified using the methods described above, the data manager may provide one or more graphical user interface widgets that, when selected, may identify changes to the field, soil, crops, tillage techniques, or application techniques nutrients. The data manager may contain a screen display in the timeline mode, a screen display in the digital table mode, or one or more editable programs. 00371 Fig. 5 illustrates an example of an implementation variant of the screen display in the time scale mode for input data. By using the screen shown in Fig. 5, the user can select a specific field and a specific date to add an event.The events displayed at the top of the timeline include the tabs: Nitrogen, Planting, Reception and

Soil. To add a nitrogen application event, the user's computer may provide an option to select the nitrogen tab. Then, the user's computer can choose a certain position on the timeline. corresponding to a specific field for information on nitrogen application in a specific field. In response to receiving a timeline position for a particular field, the data manager can display a transparent layer for the input data, allowing

From the user's computer, download data related to the application of nitrogen fertilizers, planting procedures, application of fertilizers to the soil, methods of mechanical processing, irrigation methods and other information regarding a certain field. For example, if the user's computer selects a portion of the timeline and indicates a nitrogen application, the transparent input layer may include fields for entering the amount of nitrogen to be applied, the date of application, the type of equipment used to apply the fertilizer, and any other information relating to the application of nitrogen. 0038) In an embodiment of the invention, the data manager provides an interface for creating one or more programs. In the context of this document, the term "program" means a set of data relating to nitrogen application, planting procedures, soil fertilization, tillage techniques, irrigation techniques, and other information that may relate to one or more fields and may be stored in digital data storage for reuse as a data set in other operations.

Once a program is created, it can be conceptually applied to one or more fields, and a reference to the program can be stored in digital storage, along with data identifying the fields. Thus, instead of manually entering identical data relating to the same nitrogen application to a plurality of different fields, the user's computer can create a program indicating a particular nitrogen application and then apply the program to a plurality of different fields. For example, on the timeline mode screen in FIG. 5, the top two timelines have the Fall application program selected, applying 150 pounds of nitrogen per acre in early April. The data manager can provide an interface for editing the application. In an embodiment of the invention, when a specific program is edited, each field for which a specific program is selected is edited. For example, in Fig. 5, if the Fall Application program is edited to reduce the nitrogen application to 130 pounds per acre, the top two boxes are updated with the reduced nitrogen application based on the edited program. 0039) In an embodiment of the invention, in response to receiving an edit of a field that has a selected program, the data manager deletes the field's reference to the selected program. For example, if nitrogen application is added to the upper field in FIG. 5. The interface is updated to provide information that the "Fall Application" program no longer applies to the 60 top box. Although the application of nitrogen in early April remains, the update of the program

"Fall application" does not change the application of nitrogen in April. 0040) Fig. 6 illustrates an example of a variant of the implementation of the display of the screen in the mode of a digital table for the entered data.

By using the screen shown in fig. 6, the user can create and edit information for one or more fields. The data manager may contain a digital table for entering information on the Nitrogen, Planting, Intake and Soil tabs, as illustrated in Fig. 6. To edit a specific record, the user's computer can select a specific record in the numeric table and update the value.

For example, Fig. 6 illustrates the process of performing an update of a given yield value for a second field. Additionally, the user's computer may select one or more fields to apply one or more programs. In response to receiving a program selection for a particular field, the data manager may automatically complete data entry for a particular field based on the selected program. As with the Timeline mode screen display, in response to receiving a program update, the data manager updates the records for each field associated with a particular program.

Additionally, in response to receiving an edit to one or more records for a field, the data manager may remove the selected application's reference to the field.

І0041| In an embodiment of the invention, the models and field data are stored in the storage of models and field data 160. These models contain data models created for one or more fields. For example, a crop model may contain a constructed digital model of crop development in one or more fields. In the context of this document, "model" means a stored electronic digital set of executable instructions and data elements related to each other that can receive and respond to a software or other digital call, activation, or analysis request based on specified input data, to output one or more stored output values, which may serve, among other things, as the basis for computer-implemented recommendations, display of output data, or machine control. Those skilled in the art may find it convenient to construct models using mathematical equations, but this form of expression does not limit the models set forth herein in an abstract sense;

Instead, each model in this document has a practical application on a computer in the form of stored instructions to be executed and data that implements the model (using a computer. The model data may contain a model of previous events on one or more fields, a model of the current state of one or more fields, and/or a model of predicted events on one or more fields. The model and field data may be stored in in-memory data structures, rows in a database table, flat files or numeric tables, or other forms of stored digital data.

I0042| In an embodiment of the invention, each of the instructions - potential yield modeling instructions 136, crop stress index calculation instructions 138 and yield estimation instructions 142 - contains a set of one or more pages of main memory, for example, a RAM, in the agricultural intelligent computing system 130 , into which executable instructions are loaded and which, when executed, cause the agricultural intelligent computing system to perform the functions or operations described with reference to these modules. For example, the crop stress index calculation instructions 138 may include executable instructions that are loaded into a set of pages in the VAM containing instructions that, when executed, cause the crop stress index calculation instructions described herein to be executed. Such instructions can be provided in the form of executable code in the CPP instruction set and can be compiled according to the derived code written in the language CHAMA, C,

Sat, OVOESTIME-C or in any other programming language or human-readable environment, both alone and in combination with scripts in the AMA5SVIRT language, other scripting languages and other derived programming text. The term "pages" is intended to broadly describe any area within main memory, and the specific terminology used in the system may vary widely depending on the memory architecture or the processor architecture.In another embodiment of the invention, each of the instructions potential yield modeling 136, stress index calculation instructions 138, and yield evaluation instructions 42 may also represent one or more files or drafts of derivative code stored digitally on a storage device, such as a non-volatile VAM or disk storage device in agricultural intelligent computing system 60 130 or a separate data storage system that, when compiled or interpreted, prompts the agricultural intelligent computing system to perform the functions or operations described in this document in relation to such modules. In other words, the graphical materials may represent the manner in which programmers or software developers organize or adapt the derived code for further compilation into executable code or interpretation into bytecode, or equivalent, for execution by the agricultural intelligent computing system 130. instructions in memory executables or stored derived code referred to in this section are examples of the term "modules" as used in the claimed description of the invention. 0043) The potential yield modeling instructions 136 primarily represent digitally programmed instructions that, when executed by one or more processors of the agricultural intelligent computing system 130, cause the agricultural intelligent computing system 130 to execute and store data values and develop digital crop yield models.

The instructions for calculating the agricultural crop stress index 138 when executed by one or more processors of the agricultural intelligent computing system 130 prompt the agricultural intelligent computing system 130 to execute and store data values and develop digital models of the effect of weather conditions on the yield of an agricultural crop. The yield estimation instructions 142 when executed by one or more processors of the agricultural intelligent computing system 130 cause the agricultural intelligent computing system to perform translation and storage of data values, obtain digital models of crop yield and weather effects on crop yield, and generate yield estimates based on the digital models and received field data.

I0044| The hardware/virtualization layer 150 includes one or more central processing units (CPUs), memory controllers, and other computing system devices, components, or elements, such as volatile or nonvolatile memory, nonvolatile storage, such as disk, and input devices /output or interfaces, as illustrated in FIG. 4. Level 150 may also contain program instructions that

They are designed to support virtualization, containerization, and other technologies. 0045) To illustrate a simple example, Fig. 1 illustrates a small number of central functional elements. However, in other embodiments of the invention, there may be any number of such elements. For example, embodiments of the invention may use thousands or millions of different field controller computing devices 104 associated with different users. Additionally, system 130 and/or external data server computer 108 may be implemented using one or more processors, cores, clusters, or objects M of physical machines or virtual machines configured at separate locations or combined with other elements in data centers, public computing centers or cloud computing centers. (0046) 2.2. APPLICATION PROGRAM OVERVIEW

I0047| In an embodiment of the invention, implementing the functions described herein using computer programs or other software elements that are loaded onto and executed using one or more general purpose computers causes the general purpose computers to be configured as a a machine or computer specially adapted to perform the functions described in this document. Additionally, each flowchart described further herein may serve, by itself or in combination with the description of the processes and functions formally described herein, as algorithms, blueprints, or instructions that may be used to program a computer computer or logic circuit in order to implement the functions described. In other words, the textual description herein and all graphical materials together are intended to provide a description of algorithms, plans, and instructions sufficient to enable those skilled in the art to program a computer to perform the functions described herein, in combination with the knowledge and skill but also persons, taking into account the level of skills, who are suitable for the invention and description of such types. (0048) In an embodiment of the invention, the user 102 interacts with the agricultural intelligent computing system 130 using a computing device controlling field operations 104, which provides an operating system and one or more application programs or applications, while the computing device controlling field operations 104 can also interact with an agricultural intelligent 60 computing system independently and automatically, under program control, or under logic circuit control, and direct user interaction is not always required.

Field robot controller computing device 104 is widely represented by one or more smartphones. PDAs, tablets, laptops, desktops, workstations, or any computing device capable of transmitting and receiving information and performing the functions described in the successful document. Field robot controller computing device 104 may exchange data over a network using a mobile application stored on field robot controller computing device 104 and, in some embodiments, the device may be connected, via cable 113 or a connector, to sensors 112 and/or to controllers 114. A particular user 102 may own, operate, or own and use, in conjunction with system 130, more than one field controller computing device 104 at the same time.

І0049| A mobile application may provide client-side functionality to one or more mobile computing devices over a network. In an exemplary embodiment of the invention, the field controller computing device 104 may access the mobile application via a web browser or local client application or mobile application.

The computing device of the field robot controller 104 can transmit data to and receive data from one or more interface servers using web protocols or formats, for example, NTTR, HMI. and/or 25O0M, or specific software protocols. In an exemplary embodiment of the invention, the data can be in the form of a request and input by the user, for example, field data, on a mobile computing device. In some embodiments of the invention, the mobile application interacts with hardware and software on the field robot controller computing device 104 for location tracking that determines the location of the field robot controller computing device 104 using standard location tracking technologies, such as multi-position radio tracking, global positioning systems (P), Mui-Ri positioning systems, or other methods of mobile positioning. In some cases, location data or

The data associated with the device 104, the user 3102, and/or the user account(s) may be bits obtained by means of requests to the device's operating system, or by means of a request to the mobile application to obtain data from the operating system.

ИЙ0О50| In an embodiment of the invention, the field controller computing device 104 sends data 106 to the agricultural intelligent computing system 130 that contains or includes, among other things, data elements that reflect one or more of the following: the geographic location of one or more fields, information about the techniques of mechanical treatments for one or more fields, planting of crops in one or more fields, and soil data obtained from one or more fields. Field controller computing device 104 may send field data 106 in response to user input 102 indicating data elements for one or more fields.

Additionally, the field controller computing device 104 may automatically send field data 106 when one or more data items become available to the field controller computing device 104. For example, the field controller computing device 104 may be connected to be able to exchange data with a remote sensor 112 and/or application controller 114. In response to receiving data indicating that application controller 114 has applied water to one or more fields, field controller computing device 104 may send field data 106 to agricultural intelligence computing system 130, which indicate that water has been released to one or more fields. The field data 106 considered in this description may be entered or transmitted using electronic digital data that is exchanged between person-to-person computing devices using parameterized SRI-addresses using the NTTR protocol, or other suitable communication protocols or message transfer protocols.

I0051| A commercial example of a mobile application is SI IMATE RIEGO MIEMU, available for purchase from Te Siitaiye Sogrogaiiop, San Francisco, California.

The SPIMATT RIEGO MIEMU Application/ or other application may be modified, extended or adapted to include features, functions and software code not disclosed prior to the date of this application. In one embodiment of the invention, the mobile application contains an integrated software platform that allows the agricultural producer to receive objective decisions regarding his further actions, due to the fact that it combines retrospective data about the agricultural producer's fields with other data that the agricultural producer wants to compare. The combination and comparison can be performed in real-time, and can be based on specific models that provide potential scenarios that allow the farmer to make better, more informed decisions. 00521 Fig. 2 illustrates two displays of an example logical organization of instruction sets in main memory when loading an example mobile application for execution. In Fig. 2, each named element represents an area of one or more pages in RAM

CAM or other main memory, or one or more blocks of disk storage, or other non-volatile storage, and the programmed instructions within these areas. In one embodiment of the invention, shown in (a), the mobile computer application 200 includes instructions for account-field-receiving and processing data-sharing 202, instructions for overview and warnings 204, instructions for maps in the form of a book 206 .seed and planting instructions 208. nitrogen use instructions 210, weather instructions 212, field health instructions 214 and productivity instructions 126.

И0О53| In one embodiment of the invention, the mobile computer application 200 contains instructions for the account-field-receiving and processing data-sharing 202, which are programmed to receive, convert and process field data from third-party systems through manual upload or API. Data types may include, but are not limited to, field boundaries, yield maps, planting maps, soil test results, application maps, and/or management zones. Data formats may include, inter alia, vector files, third-party output data formats, and/or Farm Management Information System (FMIS) export files. Data may be obtained by manual download, email attachments, external ARIs that add data to the mobile application, or instructions that cause APIs of external systems to extract data to the mobile application. In one embodiment of the invention, the mobile computer application 200 includes an input box. In response to receiving a selection of the application input box for the mobile computer 200 may display a graphic

From the user interface to manually upload data files and import downloaded files into the data manager. (0054) In one embodiment of the invention, the map instructions in the form of a book 206 contain layers of field map data, stored in device memory and programmed using visualization tools, and geospatial field data. This allows farmers to have handy information at their fingertips for reference, logging and visual display of field performance. In one embodiment of the invention, the overview and alert instructions 204 are programmed to provide an enhanced overview of operations important to the agricultural producer and timely recommendations for taking action or focusing on certain problems. This allows the farmer to spend time on issues that need attention to save time and protect yields throughout the season. In one embodiment of the invention, the seed and planting instructions 208 are programmed to provide seed selection, hybrid placement, and scripting tools, including variable seeding rate (VSR) scripting that is based on scientific models and empirical data. This allows farmers to maximize yield or investment efficiency through optimal seed procurement, placement and planting density.

И0О055)| In one embodiment of the invention, script generation instructions 205 are programmed to provide a script generation interface, including Variable Fertility Rate (FRT) scripts. The interface allows farmers to create scripts for farm equipment such as nitrogen application, planting and irrigation.

For example, a planting script interface may include tools to identify the type of seed to plant. After receiving the seed type selection, the mobile computer application 200 may display one or more fields divided into soil zones along with a panel identifying each soil zone and the zone name, texture, and drainage for each zone. The mobile computer application 200 may also display tools for editing or creating such zones, for example, graphical tools for graphically displaying soil zones on a map of one or more fields. Planting procedures can be applied to all soil zones, or different planting procedures can be applied to a different subset of foot zones. After creating the mobile application script, the computer 200 may make the script available for download in a format that can be read by the application controller, such as an archive format or a compressed format. Additionally and/or alternatively, the script may be sent from the mobile computer application 200 directly to the cab computer 115, and/or uploaded to one or more data servers and saved for later use. In one embodiment of the invention, nitrogen application instructions 210 are programmed to provide tools to inform nitrogen application decisions by visualizing crop nitrogen application readiness. This allows farmers to maximize yield or investment efficiency through optimal nitrogen application throughout the season.

Examples of programmed functions include, but are not limited to, image display, e.g., Z5IOCOSO images to enable graphical display of application areas and/or images generated from slave field soil data, e.g., high spectral resolution sensor data (with quality, as from 10 meters or less, due to proximity to the ground); loading of existing zones defined by agricultural producers; provision of a graphic and/or cartographic application for setting nitrogen application in multiple zones; downloading scripts to the hardware drive; tools for mass input of data and regulation; and/or had for data visualization. In the context of this document, "mass data entry" means one-time data entry and subsequent application of the same data to multiple fields defined in the system; example data may be nitrogen application data that is the same for multiple fields of the same farmer, but such bulk data entry is used to record any type of field data into the mobile computer application 200. For example, nitrogen application instructions 210 may be programmed to accept definitions of nitrogen application programs and application techniques, and to accept user input indicating application of such programs to a plurality of fields. In the context of this document, "nitrogen application programs" means stored, named data sets that combine, among other things: a name, color code or other identifier, one or more dates of application, types of material or product for each date and their quantity, the method of application or administration, such as injection or knife cut, and/or the amount or rate of application for each date, crop or hybrid,

From what is the subject of the application. In the context of this document, "nitrogen application programs" mean stored, named data sets that combine: name of application methods, previous crops; mechanical processing system, date of initial mechanical processing; one or more previous machining systems used; one or more indicators of application type, for example, application of manure. that were used Nitrogen application instructions 210 can be programmed to generate and prompt a nitrogen application graphic that indicates the anticipated application of a specified amount of nitrogen, regardless of whether an excess or shortage is predicted; in some variants of the implementation of the invention, different color indicators can signal the amount of excess or the amount of shortage. In one embodiment of the invention, the graphical display of nitrogen application includes a graphical display on the computer screen of a plurality of lines, with each line associated with and identifying a field; the data indicates what crops are planted in the field, the size of the field, the location of the field, and a graphical representation of the perimeter of the field; in each row, the timeline is divided by month, with graphic indicators indicating each nitrogen application and the amount in dots corresponding to the month names; and digital and/or colored over- or under-supply indicators, where color indicates quantity. 0056) In one embodiment of the invention, the nitrogen application graphic display may include one or more user input components, such as circular scales or sliders, to dynamically change nitrogen application programs and application techniques so that the user can optimize his application graphic display nitrogen The user can then use its optimized nitrogen application graphics and associated nitrogen application programs and application techniques to implement one or more scripts. including variable fertility rate (FRT) scripts. Nitrogen application instructions 210 may be programmed to generate and prompt the display of a nitrogen application map that indicates the anticipated application of a set amount of nitrogen, and regardless of whether an excess or deficiency is predicted; in some variants of the implementation of the invention, different color indicators can signal the amount of excess or the amount of shortage. A nitrogen application map can show the predicted application of a set amount of nitrogen and whether a surplus or shortage is predicted for different time periods in the past and in the future (daily, every Sunday, every year), the use of digital and/or color indicators can signal the amount of surplus or the magnitude of the shortage. In one embodiment of the invention, the nitrogen application map may include one or more user input components, such as circular scales or sliders, to dynamically change nitrogen application programs and application techniques so that the user can optimize the nitrogen application map, e.g. to obtain data on the desired value between excess and deficiency. The user can then use his optimized nitrogen application map and associated nitrogen application programs and application techniques to implement one or more scripts, including Variable Fertility Rate (FR) scripts.

In other embodiments of the invention, similar instructions as the nitrogen application instructions 210 are used for other nutrient applications (eg, phosphorus and potassium), pesticide applications, and irrigation programs.

I0057| In one embodiment of the invention, the weather instructions 212 are programmed to provide fresh weather data that takes into account the features of the field and forecasted weather information. This allows agricultural producers to save time and have an effective generalized indication in relation to daily operational decisions.

I0058| In one embodiment of the invention, field health instructions 214 are programmed to provide timely remote sensing images highlighting seasonal crop fluctuations and potential problems. Examples of programmed functions include, but are not limited to, a cloud check to identify possible cloud cover or cloud shadow; determination of nitrogen indicators based on field images; graphical visualization of monitored layers, for example including those related to field health, and viewing and/or sharing of monitoring information; and/or uploading satellite images from multiple sources and prioritizing images for the agricultural producer.

І0059| In one embodiment of the invention, the productivity instructions 216 are programmed to provide reporting, analysis, and inference tools using farm data for comparison, inference, and decision making. This allows the agricultural producer to achieve improved results for the next year due to objective conclusions about why the efficiency of investments remained at

From the previous level, and draw conclusions in relation to the factors that affected the yield. The performance instructions 216 may be programmed to communicate data over a network() 109 with server analysis programs running (on the agricultural intelligent computing system 130 and/or on the external data server computer 108 and executed to analyze, among other things, quantitative indicators, for example, yield, hybrids, density, C5OKOSO, soil samples or height.

Programmed reporting and data analysis may include yield variability analysis, yield benchmarking and other quantitative metrics compared to other farmers based on anonymous information collected from multiple farmers or, among other things, seed and planting data. 0060 Applications having instructions configured in this way can be implemented for different computing device platforms while maintaining the same general user interface appearance. For example, a mobile application can be programmed to run on tablets, smartphones, or server computers that are accessed through browsers on users' computers. Additionally, a mobile application configured for tablets or smartphones may provide full functionality of an application or cockpit application suitable for the display and data processing capabilities of the cockpit computer 115. For example, referring to image (B) in FIG. 2, in one embodiment of the invention, the cockpit computer application 220 may include cockpit map instructions 222, remote viewing instructions 224, collection and transmission instructions 226, engine warning instructions 228, script transmission instructions 230, and instructions regarding observation - booth 232. The source code base for the instructions in image (b) can be the same as in image (a), the executables that implement the code can be programmed to specify the platform on which they will be be performed, and provide, through the graphical user interface, only those functions appropriate to the cab platform or the full platform. This approach allows the system to determine completely different mechanisms of interaction with the user, suitable for conditions inside the cabin and different technological environment of the cabin. Map Instructions - The cockpit 222 can be programmed to provide a map view of fields, farms, and regions suitable for targeting machinery. The remote inspection instructions bo 224 may be programmed to enable, control, and provide real-time or near-real-time display of engine operation to other computing devices connected to system 130 via wireless networks, wired connectors, or adapters , and so on. The collection and transmission instructions 226 may be programmed to enable, control, and transmit data collected by the engine's sensors and controllers to the system 130 via wireless networks, wired connectors or adapters, and the like, the engine alert instructions 228 may be programmed to detect problems with the operation of the mechanism or instruments related to the cab and generate warnings to the operator. Script transmission instructions 230 may be configured to transmit scripted instructions, if configured to control the operation of mechanisms or collect data, surveillance instructions - booths 232 may be programmed to display location-based alerts and location-based information received from system 130 agricultural devices 111 or sensors 112 in the field, and to capture, manage and transmit location-based surveillance results to the system 130, depending on the position of the agricultural devices 111 or sensors 112 in the field. (0061 2.3. DATA ENTRY INTO THE COMPUTER SYSTEM

I0062| In an embodiment of the invention, the external data server computer 108 stores external data 110, including soil data representing soil composition for one or more fields and weather data representing temperature and precipitation for one or more fields. Weather data may include past and present weather data, as well as forecasts of future weather data. In an embodiment of the invention, the external data server computer 108 contains a plurality of servers hosted by various objects. For example, the first server may contain data about the composition of the soil, while the second server may contain data about the weather.

Additionally, the composition of the soil can be stored in multiple servers. For example, one server may store data reflecting the percentage of sand, silt, and clay, while a second server may store data reflecting the percentage of organic matter (OR) in the soil.

И0ОО6З| In an embodiment of the invention, the remote sensor 112 includes one or more sensors programmed or configured to perform one or more measurements. Remote sensors 112 may be airborne sensors, e.g.

With satellite, vehicle sensors, planting equipment sensors, tillage equipment sensors, fertilizer or insecticide application sensors, harvester sensors, and any other mechanism capable of receiving data from one or more fields. In an embodiment of the invention, the application controller 114 is programmed or executed with the ability to receive instructions from the agricultural intelligent computing system 130. The application controller 114 can also be programmed or executed with the ability to control the operating parameters of the agricultural vehicle or equipment. For example, an application controller may be programmed or configured to control the operating parameters of a vehicle such as a tractor, planting equipment, tillage equipment, fertilizer or insecticide application equipment, harvester equipment, or other farm equipment such as a water valve.

Other embodiments of the invention may use a combination of sensors and controllers, which are provided below by way of example only.

I0064| The system 130 may collect and receive data under the control of the user 102 on a mass basis from a large number of agricultural producers who provide data to a publicly available database system. This form of data acquisition may be referred to as "manual data acquisition" when one or more user-controlled computer operations are requested or initiated to collect data for use by system 130. As an example, the SPIMATE RIEGO X MIEMU application is available for purchase in the company Te Siitaie Sogrogaiiyop,

San Francisco? California, may operate to export data to system 130 for storage in storage 160 .

I0065| For example, seed control systems can simultaneously control planter components and receive planting data, including signals from seed sensors, via a signal loop of wires containing a CAM backbone and a point-to-point connection for logging and/or diagnostics. Seed monitoring systems may be programmed or implemented to display seeding density and other information to the user via the cab computer 115 and other devices within the system 130. Examples are set forth in U.S. Pat.

US Mo. 8,738,243 and US Patent Publication Mo. 20150094916, and this specification adopts information from these other patent specifications. bo (0066) Similarly, yield monitoring systems may include yield sensors for the harvester mechanism that send yield measurement data to the cab computer 115 or other device within the system 130. The yield monitoring systems may use one or more remote sensors 112 to obtain moisture measurements. of grain in the combine or harvester and transmitting these measurements to the user using the cab computer 115 or other device within the system 130.

I0067| In an embodiment of the invention, examples of sensors 112 that may be used with moving vehicles or mechanisms of certain types described elsewhere herein include kinematic sensors and position sensors. Kinematic sensors can contain any type of speed sensor, such as Doppler speed sensors or wheel speed sensors, accelerometers or gyro sensors. Position sensors may include, among other things, CHRO-receivers or transceivers, or mobile applications for determining the position due to UMI-Ri or cartography, programmed to determine the position based on the nearest M/I-Ri access points.

И00О68) In an embodiment of the invention, examples of sensors 112 that can be used with tractors or other moving vehicles include engine speed sensors, fuel consumption sensors, an area or distance indicator that interacts with the signals

SRS or radars, PTO speed sensors, tractor hydraulic system sensors configured to detect hydraulic parameters such as fluid pressure or flow, and/or hydraulic pump speed sensors, wheel speed sensors or wheel slip sensors. In an embodiment of the invention, examples of controllers and 14 that can be used with tractors include hydraulic distributor sensors, pressure controllers, and/or liquid consumption controllers; hydraulic pump speed controllers; speed controllers or speed controllers; coupling position controllers; or wheel position controllers providing automatic control. 0069) In an embodiment of the invention, examples of sensors 112 that can be used by equipment for planting seedlings, for example, with a seeding device or a pneumatic seeder, include seed sensors that can be optical, electromagnetic or impact sensors; pressure sensors, such as a load pin, strain gauge, pressure sensors; soil property sensors, such as reflectance sensors, moisture sensors, electrical conductivity sensors, optical residue sensors or temperature sensors; component performance sensors, such as planting depth sensors, cylinder pressure sensors, seed disc speed sensors, seed drive transducer, seed conveyor system speed sensors, or vacuum level sensors; or pesticide application sensors, such as optical or other electromagnetic sensors, or impact sensors. In an embodiment of the invention, examples of controllers 114 that can be used with such planting equipment include: a beam deflection sensor, for example, valve controllers associated with hydraulic cylinders; downforce controllers, such as controllers for valves associated with pneumatic cylinders, air pods, or hydraulic cylinders, and programmed to apply downforce to individual seeding sections or the entire planter frame; planting depth controllers, for example, linear drives; metering controllers, for example, electric seed metering drives, hydraulic seed metering drives, or clutches for switching the roll; hybrid selection controllers, such as seed metering drives, or other drives programmed to selectively exit or shut down the supply of seed, or a mixture of seed and air, from the feed channel to or from the seed dispenser or central large hopper; dosing controllers, for example, electric seed dosing drives, or hydraulic seed dosing drives; seed conveyor system controllers, for example, controllers for the seed belt conveyor motor: marker controllers, for example, a controller for a pneumatic or hydraulic drive; or pesticide rate controllers, such as dispenser drive controllers, crossing or position controllers.

In an embodiment of the invention, examples of sensors 1 and 2 that can be used with machining equipment include position sensors for tools such as coulters or discs; tool position sensors for such tools configured to determine the depth, angle of a mechanical connection, or the gap between channels: pressure sensors; or traction force sensors. In an embodiment of the invention, examples of controllers 114 that may be used with machining equipment include a clamping force controller or tool position controllers, such as controllers configured to control tool depth, mechanical connection angle, or channel spacing. bo 0071) In an embodiment of the invention, examples of sensors 112 that can be used with equipment for the application of fertilizers, insecticides, fungicides and the like, for example, are installed on a planter of an initial fertilizer application system, machines for applying fertilizers to the bottom layer of the soil, or on sprayers fertilizers, contain: sensors of indicators of liquid systems, for example, sensors of liquid consumption or pressure sensors; sensors that point to ge. that the spray head valves or liquid channel valves are open; sensors associated with tanks, for example, level sensors; sectional sensors or system-wide feed system sensors, or feed system sensors that take into account the characteristics of the rows: or kinematic sensors, for example, speed sensors located on the sprayer boom. In an embodiment of the invention, examples of controllers 114 that can be used with such equipment include pump speed controllers; valve controllers programmed to control pressure, fluid flow, direction, pulse width modulation, and the like; or positioning drives, for example, boom height, subsoil depth, or boom position. 0072) In an embodiment of the invention, examples of sensors 112. that can be used with harvesters include yield monitors, for example, a cushion deformation device or position sensors, capacitive fluid consumption sensors, load sensors, weight sensors, or torque sensors associated with with elevators or augers, or optical or other electromagnetic grain height sensors: grain moisture sensors, for example, capacitive sensors; grain loss sensors, including impact sensors, optical or capacitive sensors; header operation criteria sensors, for example, header height, header type, deck gap, feeder speed, and reel speed sensors; sensors of separator operation criteria, for example, drum gap sensors; rotor speed, pad gap or screen gap; screw position, work or speed sensors; or engine speed sensors. In an embodiment of the invention, examples of controllers 114 that may be used with harvesters include header performance criteria controllers for items such as header height, header type, deck gap, feeder speed, and reel speed controllers; controllers of separator operation criteria for components, for example, controllers of the drum gap; rotor speed, pad gap or screen gap; or auger position, operation, or speed controllers.

Zo 0073) In an embodiment of the invention, examples of sensors 112 that can be used with grain trailers include weight sensors or auger position, work, or speed sensors. In an embodiment of the invention, examples of controllers 114 that may be used with grain trailers include auger position, work, or speed controllers. 00741 In an embodiment of the invention, examples of sensors 112 and controllers 114 can be installed on unmanned aerial vehicles (UAVs) or "drones". Such sensors may include cameras with sensors effective for any range of the electromagnetic spectrum, including visible light, infrared, ultraviolet, near infrared (NIR), and the like; altimeters: temperature sensors: humidity sensors: total pressure sensors or other air flow or wind speed sensors; battery resource sensors; or devices for determining the radiating radar station and the reflected radar energy. Such controllers may include motor guidance or control devices, steering surface controllers, or controllers programmed to enable, operate, acquire data, control, and adjust any of the sensors described above. Examples are set forth in US Pat. No. 14/831,165, and this specification adopts information from these other patent specifications. 0075) In an embodiment of the invention, the sensors 12 and controllers 114 can be attached to the collection and testing of samples and soil and measuring devices, which are made with the ability or programmed to collect soil samples and perform soil chemical tests, soil moisture tests and other tests in relation to to the ground For example, the devices described in US Pat. No. 8,767,194 and US Pat. No. 8,712,148 may be used, and this description adopts information from these other patent descriptions. 0076) 2.4 PROCESS OVERVIEW - AGRONOMIC MODEL PREPARATION

I0077| In an embodiment of the invention, the agricultural intelligent computing system 130 is programmed or implemented with the ability to create an agronomic model. In the context of this document, an agronomic model is a data structure in the memory of the agricultural intelligent computing system 130 containing field data 106, for example, identification data and harvest data for one or more fields.

An agronomic model may also contain calculated agronomic parameters that describe, as it were, the conditions affecting the development of one or more crops in the field,

as well as the parameters of one or more agricultural crops, or all of them together. Additionally, the agronomic model may contain recommendations based on agronomic factors, such as crop recommendations, irrigation recommendations, planting recommendations, and harvest recommendations. Agronomic factors can also be used to calculate results for one or more crops, such as agronomic yield. Agronomic yield of a crop takes into account the amount of crops that have been grown or, in some examples, the revenue or profit generated from the crops grown. 0078) In an embodiment of the invention, the agricultural intelligent computing system 130 may use a pre-configured agronomic model to calculate agronomic parameters related to currently received location and crop information on one or more fields. The pre-configured agronomic model is based on previously processed field data including, among other things, identification data, yield data, fertilizer application data, and weather data. A pre-configured agronomic model can be cross-validated to ensure model accuracy. Cross-validation can include comparisons with experimental data, where predicted results are compared to actual results in the field, for example comparing predicted rain gauge estimates at the same site, or predicted nitrogen content measured in soil samples. 00791 Fig. C illustrates a programmed process by which an agricultural intelligent computing system generates one or more pre-configured agronomic models using field data provided by one or more data sources. Fig. C may serve as an algorithm or instructions for programming the functional elements of the agricultural intelligent computing system 130 to perform the operations described herein.

I0080| In block 305, the agricultural intelligent computing system 130 is programmed or implemented with the ability to implement agronomic data through

From the pre-processing of field data obtained from one or more data sources.

Field data obtained from one or more data sources may be pre-processed to remove distortions and data-distorting effects within the agronomic data, including measured outliers affecting the derived field data values.

Implementation options for agronomic data preprocessing include, but are not limited to, removal of data elements that are typically associated with extraneous data elements, certain data measurement points that are known to deviate too much from other data elements, data smoothing techniques, used to remove or reduce the additive or multiplicative effect of distortions, and other filtering or data extraction techniques used to provide cleanup of differences between positive and negative input data.

IOO81| In block 310, the agricultural intelligent computing system 130 is enabled or programmed to perform data set subset selection using the pre-processed field data to identify data sets suitable for initial agronomic model generation. Agricultural intelligent computing system 130 may implement data set subset selection technology including, but not limited to, genetic algorithm method, whole model subset method, sequential search method, stepwise regression method, swarm optimization method. and the method of the ant colony algorithm. For example, genetic algorithm selection technology uses an adaptive heuristic search algorithm based on the evolutionary principles of natural selection and genetics to identify and evaluate data sets within pre-processed agronomic data.

I0082| In block 315, the agricultural intelligent computing system 130 is enabled or programmed to implement field data array evaluation. In an embodiment of the invention, a certain array of field data is evaluated by creating an agronomic model and using certain quality parameters for the created agronomic model. Agronomic models can be compared using validation techniques including, but not limited to, mean squared error of one exclusion method (CM5ESM), mean absolute error, and mean percentage error. Example,

KM5ESM can cross-validate an agronomic model by comparing the predicted agronomic property value generated by the agronomic model with the previous agronomic property value that was collected and analyzed. In an embodiment of the invention, the evaluation logic of the agronomic data set is used as a feedback loop where the agronomic data set has not reached the adjusted quality parameters used during subsequent steps of selecting a subset of the data set (block 310).

I0083| In block 320, the agricultural intelligent computing system 130 is programmed or implemented to implement the creation of an agronomic model based on cross-validated agronomic datasets. In an embodiment of the invention, creating an agronomic model can implement multiple regression technology to create a pre-configured agronomic data model.

I0084| In block 325, the agricultural intelligent computing system 130 is programmed or configured to store a pre-configured agronomic data model for further evaluation of field data. 0085) 2.5 IMPLEMENTATION EXAMPLE - HARDWARE OVERVIEW

I0086| According to one embodiment of the invention, the technologies described in this document are implemented using one or more special purpose computing devices. Special purpose devices may be implemented in hardware to implement these technologies, or may contain digital electronic devices, such as one or more specialized integrated circuits (SICs) or programmable logic integrated circuits (PLCs) that are purposefully programmed to implement these technologies. or may contain one or more general-purpose hardware processors programmed to execute technologies according to program instructions in embedded software, memory, other storage, or a combination thereof.

Such special purpose computing devices can also be a combination of ordered logic implemented in hardware, SIS, or FPGAs programmed to order to perform these technologies. Special purpose computing devices can be desktop computer systems, portable computer systems, portable devices, network devices, or any other device that combines logic implemented in hardware and/or software to implement these technologies.

From I0087| For example, Fig. 4 is a functional diagram illustrating a computer system 400 on which an embodiment of the invention may be implemented. The computer system 400 includes a bus 402 or a data exchange mechanism for exchanging information, and a hardware processor 404 connected to the bus 402 for processing information. The hardware processor 404 may be, for example, a general purpose microprocessor. (0088) Computer system 400 also includes main memory 406, such as random access memory (RAM) or other dynamic storage device connected to bus 402 to store information and instructions to be executed by processor 404. Main memory 406 may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by processor 404 .

Such instructions, when stored on a non-volatile data medium accessible to the processor 404, transform the computer system 400 into a special purpose machine configured to perform the operations specified in the instructions.

I0089| The computer system 400 further includes a non-volatile memory device (VRAM) 408 or other static storage device connected to the bus 402, for storing related information and instructions for the processor 404, Storage device 410, for example, a magnetic disk, an optical disk or a solid state drive is installed and connected to bus 402 to store information and instructions. 0090) The computer system 400 may be connected via a bus 402 to a screen 412, such as a cathode ray tube (CRT), to display information to a computer user. An input device 414, included with a numeric and other keyboard, is connected to a bus 402 to exchange information and select commands for the processor 404. Another type of user input device is a cursor control device 416, such as a mouse, trackball, or cursor control keys to transmit directional information and selecting commands for processor 404 to control cursor movement on screen 412. Such input devices typically have two degrees of freedom along two axes, a first axis (eg, X) and a second axis (eg, Y), which allows the device to indicate the position on the plane. 0091) Computer system 400 may implement the technologies described herein using hardware-implemented logic, one or more SICs or FPGAs, embedded software 60, and/or software logic in combination with a computing system or computer system programs The 400 is a special purpose vehicle.

According to one embodiment of the invention, the technologies described herein are performed by the computing system 400 in response to the execution by the processor 404 of one or more sequences of one or more instructions located in the memory 406. Such instructions can be read from the main memory 406 , and from another data carrier, such as storage device 410. Execution of a sequence of instructions located in main memory 406 causes processor 404 to perform the process steps described herein. In an alternative embodiment of the invention, hardware-implemented circuits can be used instead of or in combination with software instructions. 00921 The term "data carrier" as used herein means any non-volatile data carrier that stores data and/or instructions that cause a machine to perform a specific operation. Such data carriers may contain non-volatile data carriers and/or volatile data carriers. Non-volatile storage media include, for example, optical disks, magnetic disks, or solid-state devices, such as data storage device 410 .

Volatile storage media include dynamic memory, such as main memory 406. Common forms of storage media include, for example, flexible magnetic disks, floppy disks, hard disks, solid state drives, magnetic tapes, or magnetic data carriers, CO-COM, any - any optical data carriers, any physical data carriers with spaced holes, KAM, RKOM, and ERKOM,

EGABZN-E"KOM, MMUKAM, any memory chips or cartridges.

ЙО093| Data carriers are remote, but can be used in conjunction with a data transfer medium. The data transmission medium takes part in the transmission of information between data carriers. For example, the data transmission medium includes coaxial cables, copper wire, and fiber optic cables, including the wires comprising the bus 402. The data transmission medium may also take the form of sound or light waves, such as those. generated during data exchange using radio waves or infrared waves. 0094) Various forms of media may be involved in supporting one or more sequences of one or more instructions for execution by the processor 404. For example, the instructions may initially reside on a magnetic disk or solid state storage device

From on a remote computer. A remote computer can load instructions into its dynamic memory and send instructions over a telephone line using a modem.

The local modem in relation to the computer system 400 can receive data over the telephone line and use an infrared transmitter to convert the data into an infrared signal. The infrared detector may receive the data contained in the infrared signal, and the corresponding circuitry may place the data on the bus 402. The bus 402 transfers the data to main memory 406, from which the processor 404 retrieves and executes instructions.

The instructions received by the main memory 406 may additionally be stored in the storage device 410 both before and after they are executed by the processor 404. 0095) The computer system 400 also includes a communication interface 418 connected to the bus 402. The communication interface 418 provides a two-way communication connection to the network cable 420 for data exchange, which is connected to the local area network 422.

For example, the communication interface 418 may be an integrated digital network card with comprehensive services, a cable modem, a satellite modem, or a modem to provide a communication connection for exchanging data with an appropriate type of telephone line. As another example, the communication interface 418 may be a local area network card (LAN) to provide a communication connection to exchange data with the corresponding LAN. A wireless connection channel can also be implemented. In any of these implementations, the communication interface 418 sends and receives electrical, electromagnetic, or optical signals carrying digital data streams that represent various types of information.

I0096| Network communication channel 420 typically provides the ability to transmit data over one or more networks to other data devices. For example, the network link 420 may provide a connection over a local area network 422 to a server computer 424 or data transmission equipment under the control of a service provider

Internet (I5R) 426. The IBR 426 in turn provides data transmission services over the worldwide packet data network, which is now generally referred to as the "Internet" 428. the local area network 422 and the Internet 428 use electrical, electromagnetic, and optical signals, carrying digital data streams. These signals, over various networks, and signals over network communication channel 420 and through communication interface 418, carrying digital data to and from computer system 400, are examples of forms of data transmission medium 600.

I0097| Computer system 400 may send messages and receive data, including program code, over a network(s), network communication channel 420, and communication interface 418. In an example of an Internet network, server 430 may transmit the requested code to an application application via the Internet 428 , IZR 426 , local area network 422 , and communication interface 418 .

Y0098| The resulting code may be executed by processor 404 as it is received and/or stored in storage device 410 or other non-volatile storage for further execution. 00991) 3. YIELD ASSESSMENT MODEL 01001 3.1 RECEIVED DATA

ИО1О1| Fig. 7 illustrates an example of a method for creating and using a digital model of crop potential yield based on planting date and relative maturity.

I0102| At step 700, retrospective maps are generated from the received data. Hindsight Maps means digitally stored data representing historical values associated with a crop with corresponding location values. For example, a lookback map may contain crop-related values for each longitude and latitude value or range of values. Additionally and/or alternatively, the retrospective map may include a model describing changes in values at different locations.

IO103) In steps 702, 706 and 710, a retrospective map is obtained for a crop planted in a plurality of fields for a plurality of years. In an embodiment of the invention, retrospective data is obtained for a set of fields from an external data source.

For example, the agricultural intelligent computing system 130 can be programmed to request external data from an entity that maintains statistical data on planting techniques, for example, from the National Agricultural Statistics Service (MA5B5) using an ARI call or other messaging mechanisms. Additionally and/or alternatively, agricultural intelligent computing system 130 may request data from multiple sources. For example, agricultural intellectual

The computing system may receive retrospective planting dates, actual yield figures, thal" or relative humidity values from farmers using systems provided by the agricultural intelligent computing system 130. As another example, the agricultural intelligent computing system 130 may receive test data, e.g. data collected by the Independent Scientific and Research Center for the Study of Seed Technologies (RIA8.5.T.) for certain locations.

IO104) In the context of this document, planting date means a specific date during the year on which a crop was planted. In the context of this document) relative maturity means a property that characterizes the vegetation period for a certain type of seed.

For example, different types of corn hybrids are associated with different types of relative maturity values. The value of relative ripening of corn hybrids is determined mainly by comparing the moisture content of grains for hybrids at the time of harvest. In the context of this document, actual yield figures mean retrospective yield data at a particular location.

ИО105) In an embodiment of the invention, retrospective data can be determined for locations where data is not available. For example, actual yield figures may be available for a specific location where the planting date is unknown. If a certain location is subject to an insurance procedure that requires planting within a certain time period, the agricultural intelligent computing system 130 can determine a planting date within a certain time period.

Additionally, data values for planting date, relative maturity, or actual yield values may be determined by the agricultural intelligent computing system 130 based on the relevant data. For example, relative maturity values can be obtained as hybrid seed data. The agricultural intelligent computing system 130 may be programmed to store data identifying relative maturity values for each type of hybrid seed. If the agricultural intelligent computing system 130 receives data identifying a certain type of hybrid seed, the agricultural intelligent computing system 130 can find a relative maturity value associated with a certain type of hybrid seed. because ИО1О6| Data of varying degrees of detail can be obtained. Example,

Agricultural Intelligent Computing System 130 can obtain average data such as: plantings for the county, relative maturity values and actual yield figures. Alternatively, the agricultural intelligent computing system 130 may obtain data for planting dates that take into account field specificity, relative maturity values, and actual yield values for a plurality of fields. For example, the agricultural intelligent computing system 130 may receive test data from one or more sources containing planting date, relative maturity, and actual yield values for a plurality of fields within a geographic area. In another example, the agricultural intelligent computing system 130 may receive survey data from farmers indicating field location, historical planting dates, historical relative maturity values, and actual yield values for each field. Additionally and/or alternatively, the level of detail may vary for each type of data. For example, agricultural intelligent computing system 130 may receive planting dates from a first source for each field within a geographic area and actual yield figures from a second source as average data for each county.

I0107| 3.D2 GENERATION OF RETROSPECTIVE MAPS

IOTO8)| At steps 704, 708 and 712, retrospective maps are generated from the received data. In step 704, relative maturation maps are generated from the obtained retrospective relative maturation values. In step 708, planting date maps are generated from the obtained retrospective planting date values. In step 712, actual yield maps are generated from the obtained actual yield values. As in step 700, each of the maps includes digitally stored data representing values associated with the crop with corresponding location values.

I0109| Despite the fact that Fig. 7 illustrates an embodiment of the method in which the maps are generated in the form of separate stages, in the embodiment of the invention, the stages of generating planting date maps, maps of relative ripening and maps of actual yield indicators can be performed together. For example, based on the obtained values of relative ripening and planting dates for a certain year, the agricultural intelligent computing system 130

Zo can be programmed to generate a separate map containing relative maturity values and planting dates for each geographic area.

ИО110)| In an embodiment of the invention, generation of retrospective maps includes generation of data values for locations where data is not available. For example, if planting dates are available for two thousand specific locations, agricultural intelligence computing system 130 may be programmed to use data values at two thousand specific locations to interpolate values for areas within the two thousand locations. Agricultural intelligent computing system 130 may interpolate data values for planting dates, relative maturity, and actual yield values using any neighbor interpolation, Delaunay triangulation, weighted inverse distances, thin plate splines, kriging, and/or similar interpolation methods.

ИО1111) In an embodiment of the invention, the generation of retrospective maps includes the creation of average values for certain locations. For example, agricultural intelligent computing system 130 may be programmed to obtain planting dates for certain fields for multiple years.

Agricultural intelligent computing system 130 may also receive data identifying average productivity values for a plurality of counties. Since average yield values do not correlate with planting dates with a finer degree of detail than at the county level, agricultural intelligence computing system 130 can generate county average planting date values to correlate with actual yield values. Thus, the agricultural intelligent computing system can calculate average planting dates for a county by averaging the planting dates for each field within the county or a randomly selected field within the county. In an embodiment of the invention, fields within a county are weighted based on the estimated impact on the average planting date for the county. For example, if the first field is twice as large as the second field, the agricultural intelligence computing system 130 may weight the first field twice as much as the second field when averaging planting dates. Thus, if the first field was planted on the first of the month and the second field was planted on the thirteenth of the month, the agricultural intelligent computing system 130 can calculate a weighted average of date and planting 60 for the two fields as the tenth of the month. Additionally and/or alternatively,

agricultural intelligent computing system 130 can calculate the average planting date for each county and year. 0112) In an embodiment of the invention, the generation of retrospective maps includes the translation of the received data values. For example, the resulting planting dates may initially be described as specific days of a specific month. To create a model dependent on the planting date, the agricultural intelligent computing system 130 may calculate relative planting dates for each received planting date. The relative planting date may contain the difference between the raw mean planting date and the derived planting date.

The derived planting date can be a pooled average planting date for a year across a plurality of locations, a pooled average planting date for a specific location across a plurality of years, and/or a pooled average planting date across a plurality of locations and a plurality of years.

Additionally, agricultural intelligent computing system 130 may translate identified seed types into corresponding maturity values using stored hybrid seed data. 0113) In a variant and implementation of the invention, the agricultural intelligent computing system 130 creates one or more maps separately for each year of the plurality of years.

For example, agricultural intelligent computing system 130 may create a planting date map containing planting dates within a geographic area, such as the continental United States, for a given year.

Additionally and or alternatively, agricultural intelligent computing system 130 may generate one or more maps to group multiple years. For example, a planting date map can contain planting dates by location and year. A visual display of a planting date map can contain multiple years, each displaying planting dates for a specific year. Maps for different years and locations can be reconciled in space and time. 0114) 3.3 MODELING OF POTENTIAL YIELD

IO115) In step 714, a potential yield model is generated depending on the planting patch and relative maturity based at least in part on relative maturity maps, planting date maps, and actual yield maps. For example, from

Using the maps generated in steps 704, 708, and 712, the agricultural intelligent computing system 130 can be programmed to generate a digital model of the potential crop yield as a function of random errors. Since the data in the generated maps are related to specific locations and years, the digital model may contain location dependence and time dependence. For example, agricultural intelligent computing system 130 may use the following equation:

Mo (Ho psa de, Msi reflects the potential yield of an agricultural crop in location s and year It with a certain date of planting and corresponding ripening under ideal conditions, /(Xs) is a function relating to the location and the time-sensitive covariance matrix Xsi, sho contains parameters related to planting dates and relative ripening, and csx is a location parameter and random errors that are sensitive to time. 0116) In an embodiment of the invention, the linking function /(Xxi) is a linear function of VD Xe , which contains, for a given location and year, a parameterized constant using maps. that were generated, VD, and the covariance matrix Xx, prognostic variables.

Prognostic variables in Xx may include a planting date variable and a relative ripening variable. In some embodiments of the invention, Hsi contains a variable of actual yield indicators for a specific location with a time dependence. For example, if yield rates for a particular location have decreased over the past ten years, the actual yield rate variable may contain a parameter that describes the decrease in yield over time. In additional variants of the invention, Xe contains the square of the relative ripening value and the squared value of the relative planting date to calculate more complex relationships between planting date, relative ripening and potential yield. In an embodiment of the invention, the linking function also contains a matrix p of coefficients associated with prognostic variables. While the covariance matrix Xxi may depend on location and year, in an embodiment of the invention D contains coefficients that are independent of location and time, D can be determined using any options of parameterized analysis, for example, least squares regression or general linear regressions to describe the general relationship between planting date, relative maturity, and total yield. 0117) 3.4 YIELD SIMULATION

ИО0118| The potential yield model described above models the relationship between planting date, relative maturity, and total potential crop yield for a given crop under ideal conditions. Though. that relative maturity and planting dates can be measured, the potential yield of a crop cannot be measured. Thus, to construct a potential yield model, the agricultural intelligent computing system 30 may be programmed to treat potential yield as a latent function in the actual yield model. An actual yield model may contain a potential yield and one or more values that reflect stress factors that limit overall crop yield. For example, a linear crop yield model can be displayed as shown below:

IB Code Me I Kebsi Zhbs where Xx is the total yield for a certain location and time, MUsi is the potential yield for a certain location and time, si is a covariance matrix containing stress indices for the crop, us is a location-specific set of coefficients that correspond to stress indices for agricultural crops, and isEs: is a parameter of random errors. Crop stress indices, as described in more detail in this document, reflect conditions that adversely affect optimal crop yield. Given that the impact of each crop stress index may vary by location, the set of coefficients corresponding to each crop stress index can be parameterized separately for each location or with one or more location-dependent parameters. For example, if the crop stress index reflects daytime heat stress having a greater effect on crop yield in the first location than in the second location, the corresponding coefficient for the first location may be greater than the corresponding coefficient for the second location. Since

Since the difference between the impact of the stress index for the agricultural crop does not vary greatly between different locations in the embodiment of the invention, the us is calculated with a normal distribution for each value of the coefficient with an average of uo and a variable of so. 0119) In an embodiment of the invention, the agricultural intelligent computing system 130 is programmed to generate a model of potential yield using a model of total yield. The agricultural intelligent computing system 130 may model the potential yield of an agricultural crop as a latent function of measured total yield using previous stress data for the crop and previous yield values for a particular location. For example, agricultural intelligent computing system 130 may receive data identifying temperature measurements, precipitation measurements, irrigation techniques, application of biogenic substances, and soil data for a particular location and year.

Based on the received data, the agricultural intelligent computing system 130 can model the effect of various stress indices for the agricultural crop on the overall yield of the agricultural crop. Based on the simulated effects of crop stressors and overall yield, agricultural intelligence computing system 130 can determine potential crop yield for each location and year. Then, the determined potential crop yield for each location can be used to identify the effects of planting date and relative maturity on crop yield. 0120) In an embodiment of the invention, the simulation of the actual yield also additionally includes the generation of the model as a function of the distribution of the simulated parameters. For example, each modeled parameter may be subjected to a Bayesian model such that a distribution is generated for each modeled parameter instead of an exact estimate. Due to the fact that the actual yield model is based on a probabilistic estimation of the modeled parameters, for example, relative maturity and planting dates, the model is created with a better estimate of the error in the actual yield and allows more effective decisions about risk limits. (012113.5 STRESS INDICES FOR AGRICULTURE

(0122) As described. crop stress indices are used to identify extreme cases that may stress a crop during development and may adversely affect optimal crop yield. Types of crop stress indices include, but are not limited to, flooding stress, drought stress, daytime heat stress, nighttime heat stress, early drought stress, and biogenic stress. Each of the described types of crop stress is stored in the form of a digital value calculated by a computer using the received agricultural data during a certain period. In an embodiment of the invention, a certain period used to calculate the crop stress index can be extracted from the life cycle of the crop, which is called crop phenology. 0123) 3.51 AGRICULTURAL CROP PHENOLOGY (0124) The life cycle of a maize seedling is measured using developmental stages during growth beginning with planting and ending at physiological maturity, also known as the black layer. Fig. 8 illustrates an example of a variant of the stages of corn development. The stages of corn development are divided into two main stages - the vegetative stage and the reproductive stage.

Vegetative stages of development are the stages in which a corn seedling develops from seed to fully formed plant. Vegetative stages of development are characterized by an increase in the biomass of an agricultural crop, the development of roots, stems and leaves, and its preparation for reproduction. Vegetative stages of development begin with the seedling stage, designated "ME". and end with a full visible bone "MT". A corn shoot (ME) refers to the first node of a corn seedling visible from the ground. Full visible pistil (MT) means the stage at which the pistil is fully visible, forming flowers when pollinated. Between the ME and MT stages, there are many vegetative stages that describe the development of a corn seedling by how much of the upper leaf is visible at the leaf node.

Example. "U2" means the stage of development at which two leaves have fully extended to a visible leaf node, and "M12" means the stage of development at which twelve leaves have fully extended to the visible leaf node.

From IO125| Reproductive stages describe the stages from the point at which the physical maturation of the maize seedling can occur. The reproductive stages begin at the stage of shedding of uterine columns "NO" and end at the stage of physiological maturation "Wb", also known as the stage of the black layer. Between the NI and Nb stages are the stages that describe the development of a corn seedling. For example, "H2" is called the bubble stage, when the grains are described as white in color and bubble-like in shape.

The "AZ" stage is called the milky stage, when the grains have a yellow color on the outside with a milky internal liquid. Stage "H4" is called the phase of wax maturity, when the milky internal liquid is condensed to a paste-like consistency. Stage "B5" is called the stage of the mark on the grain, when the grains show a mechanical mark from the nail. (0126) The phenological stages of a corn seedling can be tracked based on external factors that appear on individual corn seedlings. For example, the phenological development of corn seedlings is highly dependent on the accumulation of heat by the corn seedlings, which promotes the development of the corn seedling. Heat accumulation can be measured by maximum and minimum daytime temperatures. In an embodiment of the invention, degree-days of growth (500) are used to track various stages of corn seedling development. Growth degree days (500) can be calculated using different data obtained and different limit values. For example, growth degree-days (500) can be calculated as:

Ttah Ye Tem

Daily BO s yan t Zhrohe eh Eto

Where 7 2 is the daily average temperature calculated from the daily maximum and minimum temperature. Tiase is the lower limit value of the temperature, when no significant development of the seedling is observed. In an embodiment of the invention, the limit value can be set for T tah and Ttlip. For example, a limit value of 86 "E (30 "C) can be set for Tmax such that Tmax is set to 86 "E (30 "C) when the temperature exceeds 86 "PE (30 "C) and the limit value is 50 "E (10 "C) can be set for Trtip so that Ttip is set to 50 "EE (10 7C) when the temperature drops below 50" (10750).

ИЙО127| Thus, when the average daily temperature does not exceed the lower temperature limit, the development of the corn seedling is not observed. Fig. 9 illustrates an example of a table where the number of growing stage days is used to determine the beginning and end of different phenological stages of development. For example, after 177 days of growing degree (2400), stage U2 for a corn seedling begins. At 1240 degree-day of growth, the reproductive stage of NI begins. Though. that Fig. 9 mainly illustrates various physiological stages of development for a certain agricultural crop, in an embodiment of the invention, different types of seeds can reach physiological stages at different times.

For example, the threshold value for the M2 stage of a maize seedling with a high value of relative maturity, as shown in Fig. 9, may occur after 177 degree-days of dew in (400).

The growth degree-days (300) measurement is particularly useful when identifying certain weather conditions to indicate correlations with different developmental stages during the growth of a corn seedling. (01281 3.5.2 STRESS CAUSED BY FLOODING

Y0129| Flooding of fields is extremely detrimental to the development of agricultural crops.

For example, standing water can cover the tops of corn seedlings, which can cause them to suffer from excess water and depleted soil oxygen levels.

A lack of oxygen in the soil can prevent the seedling from performing its functions, for example, the absorption of biogenic substances and water, which negatively affects the overall yield of the agricultural crop. Flooding stress can be used to quantify the negative impact of recorded flooding to accurately predict crop yields. In an embodiment of the invention, the stress caused by flooding is calculated as the sum of daily water leakage that exceeds the above-mentioned certain limit value of water leakage. Water seepage means that water that is not absorbed by the soil flows from above the soil. When measuring leakage, some leakage may be the result of water not being absorbed as fast as the planned water collection is delivering the water. Thus, only such a leak that exceeds the permissible limit value,

Zo is seen as contributing to flooding. For example, if the allowable limit for a field is set to 3.75 inches (9.53 cm), then any measured leakage above 3.75 inches (9.53 cm) is counted toward the total leakage for the flooding stress calculation.

In an embodiment of the invention, the first stage of flooding stress may be calculated as the sum of daily runoff exceeding 3.75 inches (9.53 cm) during the period from seed to U8, where the first stage covers the period from planting to U8. In other variants of implementation of the invention, the limit value can be adjusted based on the composition of the soil and the degree of absorption of water by the soil. 01301 3.5.3 STRESS CAUSED BY DROUGHT

ИО131| Inadequate soil moisture during the development period can lead to a decrease in the yield of corn, as the assimilation of biogenic substances, absorption and transport decreases without the necessary amount of water in the soil. Stress index. caused by drought, can be used to calculate the level of soil moisture inconsistency during different stages of crop development. In an embodiment of the invention, drought stress is calculated as the sum of daily soil moisture records below a certain threshold, for example, if a certain drought threshold is below 20 95, then all daily soil moisture records below 20 95 are summed together for of measured developmental stages to generate drought stress for the Crop Stress Index. In an embodiment of the invention, the first stage of stress caused by drought is calculated as the sum of all records of daily soil moisture in between stages

U8 and M16. where the soil moisture values are lower than the threshold drought value of 20 95. In other embodiments of the invention, drought stress can be calculated as the second stage and the third stage of drought stress, where the second stage covers stages B1 to H2, and the third stage covers stages from VZ to H5. (01321 3.5.4 STRESS CAUSED BY EARLY DROUGHT (0133) As described earlier, inadequate soil moisture during development periods can lead to a decrease in corn yield, in particular, at the early stages of development. In an embodiment of the invention, stress caused by early drought can be measured as the sum of rainfall minus runoff when daily rainfall minus runoff ranges from zero to 2.5 in bo (6.35 cm). Rainfall minus runoff equals the amount of water absorbed by the soil. Only by counting the water absorbed by the soil , when the value was less than 2.5 inches (6.35 cm), early drought stress indicates that a small amount of water has been absorbed. In an embodiment of the invention, early drought stress covers the range from planting to Ub 01341 3.5 .5 DAY HEAT STRESS

ИО135| High daytime temperature is extremely detrimental to the development of the agricultural crop of corn. High daytime temperature, above a certain temperature value, can negatively affect the development of corn during the vegetative and reproductive stages, and can negatively affect the yield of corn.

In addition, extreme daytime temperatures and high temperatures can cause premature drying of the soil, which can lead to drought. In an embodiment of the invention, daytime heat stress can be calculated as the sum of the number of degrees Fahrenheit for each day when the temperature exceeds the threshold value.

ИО136| For example, agricultural intelligent computing system 130 may calculate daily heat stress during a period covering stages M10 through M16, where the defined threshold value is 93 degrees Fahrenheit (34 "C). In this example, each daily maximum temperature between developmental stages with M1O0 to M16 is measured to determine if it exceeds 93 degrees F. If none of the daytime temperatures exceed 93 degrees F, then daytime heat stress during that period will be zero. However, if the maximum temperature between developmental stages

M10 and M16 exceeds 93 degrees for two times, and is equal to 100 degrees each time, then the daily heat stress will be equal to the sum of (100-93) for both days, and will be equal to 14 degrees for this period.

ИО137| In an embodiment of the invention, the instructions for calculating the stress index 138 provide instructions for determining the first stage of daytime heat stress when the first stage includes phenological stages from M10 to MIb, and set the limit value at 93 degrees. In an embodiment of the invention, the instructions for calculating the stress index 138 provide instructions for calculation of the second stage and the third stage of daytime heat stress, where the second stage covers the stages from NI to HV and the third stage covers the stages from BZ to H5, and the specified temperature limit is 93 degrees Fahrenheit.

From 01381 3.6.5 NIGHT HEAT STRESS

ЙО139| High night temperature is extremely detrimental to the development of the agricultural crop of corn. High night temperatures can induce sugar metabolism in maize seedlings to a high degree during the night. This can lead to excessive sugar consumption by the seedling during the development period, instead of releasing sugar to form grains.

A high metabolism of the seedling during the night can lead to a decrease in yield, since the seedling does not have enough resources to form healthy grains during the reproductive period. Nocturnal heat stress can be calculated as the sum of the number of degrees Fahrenheit for each night that the temperature exceeds a set threshold. For example, agricultural intelligent computing system 130 may calculate nighttime heat stress as the sum of the minimum daytime temperature that is higher than the minimum temperature threshold, which is equal to: 70 degrees Fahrenheit (21 "C).

In an embodiment of the invention, instructions for calculating the stress index 138 provide instructions for calculating the first stage of nighttime heat stress, when the first stage covers stages from K1 to

K5, while the minimum temperature limit is 70 degrees Celsius

Fahrenheit. (01401 3.5.7 STRESS CAUSED BY THE USE OF BIOGENIC SUBSTANCES

Y0141| The lack of one or more biogenic substances can affect the potential yield of an agricultural crop. For example, nitrogen deficiency describes the effect of a crop's inability to obtain the optimal amount of nitrogen during crop development. Each agricultural crop has a different optimal amount of nitrogen, which determines the minimum amount of nitrogen, below which the indicator negatively affects the development of the agricultural crop. The optimal amount of nitrogen can change the entire development cycle of an agricultural crop. The stress caused by the application of biogenic substances can be calculated as the difference between the simulated or measured amount of biogenic substances in the soil and the value that reflects the minimum value of biogenic substances that can be assimilated by the crop, the value below which negatively affects the development of the crop. The stress caused by the application of biogenic substances can also be calculated as the number of days in which the agricultural crop is unable to obtain one or more biogenic substances necessary for it. Thus, if the nitrate level in the soil is below the minimum threshold value for five days, the agricultural intelligent computing system 130 can identify the yield in response to the stress caused by the application of nitrogen for five days. (0142) 3.6 MODEL REINFORCEMENT 0143) In an embodiment of the invention, the agricultural intelligent computing system 130 is programmed to use previous data at one or more locations to strengthen models of potential yield and total yield.

The agricultural intelligent computing system 130 may initially obtain preliminary planting dates identifying one or more planting dates, relative maturity, and yield for a plurality of experimental fields. The agricultural intelligent computing system 130 can also receive preliminary data on certain conditions that identify one or more weather phenomena received on multiple experimental fields. Using planting dates, relative maturity values, and weather data, the agricultural intelligent computing system 130 can calculate estimated potential crop yields for multiple fields. The agricultural intelligent computing system 130 may compare the estimated yield of the crop with the actual yield of the crop to determine whether the model properties determine the effect of planting dates and relative maturity on the total yield of the crop. The agricultural intelligent computing system 130 can use the results of the comparison to update the models.

Example. if the simulated yield values associated with a particular relative ripeness value are typically lower than the actual yield value, the agricultural intelligence computing system 130 may update the coefficients associated with the relative ripeness predictor variables to increase the influence of the particular relative ripeness value on yield. 0144) In an embodiment of the invention, the preliminary data contain measurements where one or more factors are kept constant. Agricultural intelligent computing system 130 can be programmed to use previous data from

With one or more factors held constant to enhance estimates of potential yield, taking into account relative maturity, planting dates and location. For example, one set of measurements may contain multiple locations where a single crop was planted on a given date. Since the planting date and relative maturity do not change, the agricultural intelligence computing system 130 can determine the effect of location on potential yield. The second set of measurements may contain multiple locations with different crops planted on the same date. Using this data, the agricultural intelligent computing system 130 can identify location-specific effects of relative maturity on potential yield and overall effects of relative maturity on potential yield. types of seeds. Based on the results of the described measurements, the agricultural intelligent computing system 130 can update the potential yield model for better correlation with previous data. For example, if historical data indicates a high variation in yield based on relative maturity data that is underrepresented in the potential yield model, the agricultural intelligence computing system 130 may update coefficients associated with relative maturity predictor variables to increase the effect of relative maturity values on yield . (01454. USE MODEL

ЙО146| Returning again to Figs. 7. at step 716, the values of the actual yield indicators for the agricultural crop planted in a certain field are obtained.

For example, the agricultural intelligent computing system 130 may be programmed to receive preliminary crop yield data from the field controller computing device 104 associated with one or more fields owned by the user of the field controller computing device 104. Additionally, in an embodiment of the invention agricultural intelligent computing system 130 also obtains preliminary planting dates and relative maturity values for certain fields. With the use of actual yield values and previous planting dates, and relative maturity values, the agricultural AI computing system 130 can further improve the model of potential for a particular location.

I0147| In step 718, a certain potential yield for a certain field is calculated by a potential yield model based at least in part on the actual yield values for the crop planted in the certain field.

For example, agricultural intelligent computing system 130 may be programmed to input a specific relative maturity value, a specific planting date, and actual yield values into a potential yield model of a specific field. (01481) 41 ASSESSMENT OF TOTAL YIELD OF AGRICULTURAL CULTURE 01491 In an embodiment of the invention, the agricultural intelligent computer system 130 is programmed to estimate total yield based on a potential yield model for a specific location, planting date, relative maturity value, and actual yield indicators. For example, the agricultural intelligent computing system 130 may provide an interface for the field control computing device 104 to select a field, enter a planting date and relative maturity value, and request an estimate of the total yield of the agricultural crop. The interface may contain options for choosing the date of planting and the type of seeds. The agricultural intelligent computing system 130 can translate the selected dates into relative ripeness values.

Agricultural intelligent computing system 130 can translate seed type into relative maturity values using stored seed data. By inputting the planting date, relative maturity value, actual yield figures, and field location, the agricultural intelligent computing system 130 can calculate the potential yield for a particular field.

ЙО150| In some embodiments of the invention, the agricultural intelligent computing system 130 is programmed to determine the estimated total yield for a particular field prior to entering a planting date. For example, a farmer can request a forecasted yield for a particular field as part of the planting phase. In an embodiment of the invention, when crop stress data is not available, the agricultural intelligent computing system 130 may display the potential yield as a maximum value on the field controller's computing device

104. Additionally and/or alternatively, agricultural intelligent computing system 130 may model total yield for the crop using estimated values for crop stress indices.

IO151) In an embodiment of the invention, the agricultural intelligent computing system 130 can be programmed to determine estimates of the shaking index for a crop based on previous weather data and crop instruction data for a specific location. For example, the agricultural intelligent computing system 130 can be programmed to receive preliminary data on temperature, soil moisture, precipitation, and/or biogenic substances for a particular field. Temperature and precipitation data may be received from the external data server computer 108 and/or one or more sensors. located on or near a certain field. Data on soil moisture and data on biogenic substances can be obtained from the computing device controlling field work 04 and/or one or more sensors located on or near a certain field. Additionally and/or alternatively, the agricultural intelligent computing system 130 may model previous soil moisture and biogenic matter in the soil based on received data indicating rainfall, irrigation application, and/or biogenic matter application practices.

ИО152| The agricultural intelligent computing system 130 may calculate a preliminary crop stress index based on previous weather data and crop guidance data for a particular location.

Based on previous crop stress indices, the agricultural intelligent computing system 130 can estimate subsequent crop stress indices. For example, the agricultural intelligent computing system and 130 may take the mean, median, or more general value of each stress index for use as an estimated crop stress index. Additionally and/or alternatively, agricultural intelligent computing system 130 may be programmed or implemented to receive certain trends in crop stress indices and model certain trends. For example, if crop stress due to high temperature has been steadily increasing over the past five years,

agricultural intelligent computing system 130 may model an increase in crop stress due to high temperature and use the simulated stress index for heat stress in the estimated crop stress indices.

ЙО153| In some embodiments of the invention, the agricultural intelligent computing system 130 uses the following weather conditions and planting methods to estimate the stress of the agricultural crop for a certain period of development. For example, the agricultural intelligent computing system 130 may receive one or more weather forecasts identifying the next temperature and precipitation values for the next time period. Agricultural intelligent computing system 130 may be programmed to estimate crop stress indices based on weather forecast data. Additionally and/or alternatively, the agricultural intelligent computing system 130 may be programmed to receive data about planting techniques from the field control computing device 104.

For example, agricultural intelligent computing system 130 may provide an interface for entering irrigation dates, then planned, and application dates of biogenic substances. Based on scheduled irrigation dates and biogenic applications, the agricultural intelligence computing system 130 may be programmed to generate estimated crop stress indices based on available crop water and ha of biogenic in one or more fields. (0154) Using the estimated stress of the crop and the simulated potential yield for the crop, the agricultural intelligent computing system 130 can generate an estimate of the total yield for the crop at a particular location with specific planting date and relative maturity values. In an embodiment of the invention, the total yield estimate contains a range of values. For example, the agricultural intelligent computing system 130 may identify errors in estimates of crop stress indices and propagate the errors to the estimated total yield for the crop.

Additionally, a range of total yield values can be generated using

From the parameters of random errors in the model of potential yield and total yield.

The random error parameters can be assumed to be normally distributed with zero mean and uniformly distributed root mean square deviation. 0155) In an embodiment of the invention, the agricultural intelligent computing system 130 can be programmed to update the estimate of the total yield during the growing season. For example, using the methods described above, the agricultural intelligent computing system 130 can estimate stress indices of the agricultural crop for the period of development in a certain field. During the stages of crop development, the agricultural intelligent computing system 130 can be programmed to improve estimates of crop stress indices based on the received data. The agricultural intelligent computing system 130 can be programmed to receive data on temperature, precipitation, soil moisture and/or application of biogenic substances for one or more fields from an external server, one or more sensors on one or more fields, and/or a field management computing device robots 104. Based on the received data of temperature, precipitation, soil moisture and/or application of biogenic substances, the agricultural intelligent computing system 130 can be programmed to calculate crop stress indices for the crop in one or more fields during the current growing season.

IO156) For the time period in which measurements are available to calculate the crop stress indices, the agricultural intelligent computing system 130 may be programmed to replace the estimated crop stress indices with the calculated crop indices. For periods of time in which measurements are not available, the agricultural intelligent computing system 130 may be programmed to update estimates of crop stress indices based on recent measurements. For example, if the temperature during the growing season is, on average, five degrees Celsius higher than the predicted temperature, the agricultural intelligent computing system 130 may be programmed to estimate updated crop stress indices to account for the higher predicted temperature. 60 I015714.2 RECOMMENDATIONS FOR PLANTING DATE

IO158) In an embodiment of the invention, the agricultural intelligent computing system 130 can be programmed to use a potential yield model and/or a total yield model to generate one or more recommendations for a certain type of seed. For example, the agricultural intelligent computing system 130 may be programmed to receive a request from the field controller computing device 104 for planting date recommendations. The agricultural intelligent computing system 130 may be programmed to provide an interface for selecting a specific type of seed hybrid or directly entering a specific relative maturity value. If the agricultural intelligent computing system 130 receives a selection of a particular type of seed hybrid, the agricultural intelligent computing system 130 may be programmed to translate the particular type of seed hybrid into a relative maturity value. For example, the agricultural intelligent computing system 130 may be programmed to store data in a data model in the field data store 160 identifying a plurality of seed types and a plurality of corresponding relative maturity values.

Y0159| Based on the obtained relative maturity value, the agricultural intelligent computing system 130 may be programmed to use the model described above to identify a planting date that maximizes the potential yield and/or total yield of the crop. For example, agricultural intelligent computing system 130 may calculate potential yield and/or total yield for the resulting relative maturity value and each planting date within a certain time period.

The agricultural intelligent computing system 130 may identify a planting date associated with a higher calculated potential yield and/or total yield. In response to identifying a planting date associated with a higher calculated potential yield and/or total yield, the agricultural intelligent computing system 130 may send a planting date recommendation to the field management computing device. 0160) 4.3 SEED RECOMMENDATIONS

Zo 0161) In an embodiment of the invention, the agricultural intelligent computing system 130 is programmed to use the potential yield model and/or the total yield model to generate one or more recommendations for a certain type of seed. For example, the agricultural intelligent computing system 130 may receive a request for seed type recommendations from the field management computing device 104. The agricultural intelligent computing system 130 may provide an interface for selecting a specific planting date or a range of specific planting dates. After obtaining a specific planting date or a range of specific planting dates, the agricultural intelligent computing system 130 may calculate the potential yield and/or total yield for each relative maturity value for a specific planting date, or for each planting date within a range of specific planting dates. The agricultural intelligent computing system 130 may determine a relative ripeness value associated with higher potential yield and/or total yield and send recommendations regarding the relative ripeness value to the field controller computing device 104 .

Additionally and/or alternatively, agricultural intelligence computing system 130 may identify one or more hybrid seed types associated with an identified relative maturity value from seed data stored in model and field data storage 160 and send recommendations for one or more types of seed hybrids to the computing device controlling field work 104. 0162) In an embodiment of the invention, the agricultural intelligent computing system 130 can be programmed to generate seed type recommendations in response to determining that a certain date has passed without planting a crop. For example, agricultural intelligent computing system 130 may initially recommend a planting date based on a specific seed type, a seed type based on one or more specific planting dates, or a combination of planting date and seed type for a specific location. A combination of planting date and seed type can be identified by calculating the potential yield and/or total yield for a particular location and each planting date and seed type combination. Specific parameters, such as available seed or planting season time constraints, can be imposed to reduce 60 the number of calculations. When the recommended or selected planting dates have passed,

agricultural intelligent computing system 130 may determine whether a crop has been planted in one or more fields. For example, the agricultural intelligent computing system 130 may query the field controller computing device 104 to indicate whether a crop has been planted in response to determining that a certain date has passed and the agricultural intelligent computing system 130 has not received information that the agricultural crop has been planted. the crop was planted in one or more fields. In response to receiving information that the crop has not been planted, the agricultural intelligent computing system 130 may calculate the potential yield and/or total yield for the next possible planting dates using a plurality of relative maturity values.

ИО163| Agricultural intelligent computing system 130 may be programmed to determine one or more relative maturity values and one or more subsequent planting dates associated with higher calculated potential yield and/or total yield. If the agricultural intelligent computing system 130 determines that the value of relative maturity that is different from the original value of relative maturation, the agricultural intelligent computing system 130 can send recommendations to switch to the type of seed that corresponds to the determined value of relative maturation. The agricultural intelligent computing system 130 may also send recommendations to plant a recommended seed type on one or more planting dates on which the determined seed type will provide maximum potential yield and/or total yield for one or more fields. 0164) In an embodiment of the invention, the agricultural intelligent computing system 130 is programmed to determine recommended relative ripening values for different time periods. For example, agricultural intelligence computing system 130 may determine a first relative ripeness value associated with higher potential yield and/or total yield for planting dates within the next five days, and a second relative ripeness value associated with higher potential yield and/or total yield for planting dates within a range of five to ten days from the current date. If a higher potential yield and/or total yield is associated with the first value of relative maturity, the agricultural intelligent computing system 130 may send recommendations for planting seeds associated with the first value of relative maturity on a specific date within the next five days. Additionally, the agricultural intelligent computing system 130 may send information that the farmer should instead plant the seed associated with the second relative maturity value if the farmer plans to plant the crop between the fifth and tenth day from the current date. 0165) 5. ADVANTAGES OF CERTAIN EMBODIMENTS OF THE INVENTION (0166) Using the technologies described herein, a computer can provide total crop yield data that is otherwise unavailable. For example, the technologies described herein may determine, for a particular field, a specific crop to plant and a specific planting date that will yield the maximum yield of the crop. The performance of an agricultural intelligent computing system is enhanced using the technologies described herein by creating accurate models with high computational efficiency, thereby reducing the amount of memory used to model total crop yields. In addition, the technologies described herein can be used to create application parameters for the application controller, thereby increasing the performance of the agricultural machinery controlled by the application controller. (01671 6. ADDITIONAL AND ALTERNATIVE OPTIONS

I0168| In the preceding description, embodiments of the invention are described with reference to numerous specific details that may vary depending on the embodiment.

Accordingly, the description and graphic materials should be considered illustrative and not restrictive. The exclusive and only indicator of the scope of this invention, and what was assumed by the applicants as the scope of this invention, is the literal and equivalent scope of the claims resulting from this patent application in the specific form in which such claims are published, including any subsequent changes.

Zo

Claims (1)

FORMULA OF THE INVENTION 1. A method of controlling the operating parameters of agricultural equipment, including the steps of: receiving, via a network on a server computer system containing one or more processors and a digital memory, first electronic digital data containing a plurality of values that represent retrospective relative maturity for a crop planted in multiple fields over multiple years; generating, using digitally programmed instructions for modeling potential yields on the server computer system, one or more relative maturity maps from a plurality of values representing retrospective relative maturity data for the respective location; receiving, via a network on the server computer system, second electronic digital data comprising a plurality of values that represent retrospective planting dates for a crop planted in a plurality of fields over a plurality of years; generating, using digitally programmed potential yield simulation instructions on the server computer system, one or more planting date maps from a plurality of values representing retrospective planting date data for the respective location; receiving, via a network on a server computer system, third electronic digital data containing a plurality of values that reflect actual yield values for a crop planted in a plurality of fields for a plurality of years; generate, using digitally programmed potential yield simulation instructions on the server computer system, one or more maps of actual yield rates from a plurality of values representing actual yield rates for the respective location; generating, using digitally programmed potential yield modeling instructions on a server computer system, a planting date and relative maturity dependent potential yield model based, at least in part, on one or more relative maturity maps, one or more planting date maps, and one or more maps of actual yield indicators, and the potential yield model is based, at least in part, on the location of the predictor variables and on the time-sensitive covariance matrix of the predictor variables; receiving, via a network on a server computer system, fourth electronic digital data containing a plurality of values that reflect actual yield values for a particular field; calculate, using digital programmed yield estimation instructions on a server computer system, by means of a potential yield model, a specific potential yield for a specific field based, at least in part, on a plurality of values representing actual yield values for a specific field; generate one or more planting date recommendations or seed type recommendations based, at least in part, on input from the crop potential yield model; generating one or more scripts for the application controller based on one or more planting date recommendations or seed type recommendations; sending one or more scripts to the application controller, wherein the application controller executes the one or more scripts to cause the application controller to control the operating parameters of the agricultural equipment. 2. The method according to claim 1, which additionally includes steps in which: receiving, through a network on a server computer system, fifth electronic digital data containing a set of values that reflect previous weather observations for a specific geographic location; calculate, using digitally programmed stress index calculation instructions on a server computer system, one or more crop stress values from a plurality of values reflecting previous weather observations to generate one or more location-specific stress indices; create, using digital programmed yield estimation instructions on the server computer system, for each specific geographic area, a covariance matrix in computer memory containing one or more stress indices that take into account the specifics of the geographic location; calculates, using digitally programmed yield estimation instructions on a server computer system, a geographic area specific crop yield based, at least in part, on a covariance matrix comprising one or more geographic area specific stress indices and a specific potential yield for a specific field. 3. The method according to claim 2, which additionally includes the steps of: receiving, via a network on a server computer system, information that one or more agricultural crops are planted on a certain field; receiving, via a network on a server computer system, six electronic digital data containing a plurality of values that represent received agricultural data points for a particular field at a particular time, wherein the received agricultural data points include at least one received temperature record, soil moisture record and rainfall record; calculating, using digitally programmed stress index calculation instructions on the server computer system, updated crop stress index values from the received agricultural data points to generate one or more crop stress indices that account for the specificity of the geographic area, wherein each of the updated stress indices of agricultural crops, taking into account the specifics of the geographical area, contains one or more values of calculated stresses of agricultural crops for a specific field during a specific period of time; create, using digitally programmed yield estimation instructions on a server computer system, for a specific field, an updated covariance matrix in computer memory containing one or more stress indices that take into account the specifics of a geographic location; calculate, using digitally programmed yield estimation instructions on a server computer system, an updated crop yield that accounts for the specificity of the geographic area based at least in part on the updated covariance matrix and the specific potential yield for the specific field. 4. The method according to claim 1, which additionally includes the steps of: storing in the digital memory Zo of the server computer system relative ripening data of the agricultural crop containing a plurality of types of seeds and a plurality of related relative ripening values; receive, through the network on the server computer system, the proposed planting date for a specific field; determining, using digitally programmed yield estimation instructions on a server computer system, from a potential yield model a proposed planting date for a particular field, and from a plurality of values representing actual yield values for a particular field, a particular value of relative maturity that will yield the maximum potential yield for a specific field; identify, using digital programmed yield estimation instructions on the server computer system, in the data of relative ripening of the agricultural crop, a specific type of seed corresponding to a certain value of relative ripening; send, via the network to the field monitoring computing device, recommendations for a specific type of seed for a proposed planting date and a specific field. 5. The method according to claim 1, which additionally includes the stages of: receiving, through a network on a server computer system, the proposed value of relative ripening for a specific field; determining, using digitally programmed yield estimation instructions on a server computer system, from the potential yield model a suggested relative maturity value for a particular field, and from a plurality of values representing actual yield values for a particular field, a particular planting date that will produce the maximum potential yield for a specific field; sending, via the network to the field control computing device, recommendations for a specific planting date for a suggested relative maturity for the specific field. b. The method according to claim 5, which additionally includes the steps of: storing, in the digital memory of the server computer system, relative ripening data of an agricultural crop containing a plurality of seed types and a plurality of associated relative ripening values; determining, using digital programmed yield estimation instructions on the server computer system, that a specific planting date has passed, using yield estimation instructions for digital programmable logic; receive, through the network on the server computer system, information that the agricultural crop was not planted on a specific field; determining, using digitally programmed yield estimation instructions on a server computer system, from the potential yield model a plurality of values representing actual yield values for the particular field and one or more current dates or proposed next planting dates, a particular relative maturity value that differs from the proposed value of relative maturity and will give the maximum potential yield for a particular field; determining, using digital programmed yield estimation instructions on the server computer system, in the relative maturity data for the crop, a specific type of seed corresponding to a specific value of relative maturity; sending, via the network to the field monitoring computing device, recommendations for a specific type of seed for a proposed next planting date and for a specific field. 7. The method of claim 1, which further includes the steps of: receiving, via a network on a server computer system, fifth electronic digital data containing a plurality of values that reflect previous planting dates and previous relative ripening of the plurality of fields ; receiving, via a network on a server computer system, six electronic digital data containing a plurality of values that reflect received agricultural events on a plurality of fields; calculating, using digitally programmed yield estimation instructions on the server computer system, a simulated crop yield for each field of the plurality of fields based at least in part on the fifth electronic digital data, the sixth electronic digital data, and the potential yield model; receiving, via a network on the server computer system, the seventh electronic digital data containing a plurality of values that reflect the obtained yield of the agricultural crop for each field of the plurality of fields; calculate, using digitally programmed potential yield modeling instructions on the server computer system, an updated potential yield model based, at least in part, on the simulated crop yield for each field of the plurality of fields and the resulting crop yield for each field on the plurality of fields. 8. The method of claim 1, which further includes the step of: generating, using digitally programmed instructions for modeling the potential yield on the server computer system, a model of the potential yield as a linear function containing a constant parameter multiplied by a set of covariates. 9. The method according to claim 8, which is characterized by the fact that the set of covariates contains the planting date parameter, the square of the planting date parameter, the relative ripening parameter, the square of the relative ripening parameter, and the actual yield parameters parameter. 10. The method according to claim 1, which further includes the steps of: determining, using digitally programmed simulation instructions, a potential yield on a server computer system based, at least in part, on one or more maps of relative maturity, one or more maps of planting dates and one or more maps of actual yield indicators, dependence of potential yield on location; generate, using digitally programmed potential yield modeling instructions on a server computer system, a potential yield model as a linear function containing a constant parameter multiplied by a set of location-dependent covariates. 11. A computer-readable non-volatile data carrier containing instructions that, when executed by one or more processors, cause the execution of a method of controlling the operating parameters of agricultural equipment, the data carrier containing instructions for: obtaining first data containing a plurality of values that reflect retrospective relative maturity for a crop planted in multiple fields over multiple years; generating one or more relative maturation maps from the plurality of values representing the retrospective relative maturation for the corresponding location; receiving second electronic digital data comprising a plurality of values representing retrospective planting dates for a crop planted in a plurality of fields over a plurality of years; generating one or more planting date maps from a plurality of values representing retrospective planting dates for the corresponding location; receiving third electronic digital data containing a plurality of values that reflect actual yield values for a crop planted in a plurality of fields for a plurality of years; generating one or more maps of actual yield indicators from a plurality of values representing actual yield indicators for the corresponding location; generating a potential yield model dependent on planting date and relative maturity based, at least in part, on one or more relative maturity maps, one or more planting date maps, and one or more actual yield maps, wherein the potential yield model is based at least in part on , on the location of prognostic variables and on the time-sensitive covariance matrix of prognostic variables; receiving fourth electronic digital data containing a plurality of values that reflect actual yield values for a particular field; calculating, by a potential yield model, a specific potential yield for a specific field based, at least in part, on a plurality of values representing actual yield values for a specific field, and generating one or more planting date recommendations or seed type recommendations based on at least partly, the initial data obtained from the model of the potential yield of agricultural crops; generating one or more scripts for the application controller based on one or more planting date recommendations or seed type recommendations; sending one or more scripts to the application controller, wherein the application controller executes the one or more scripts to cause the application controller to control the operating parameters of the agricultural equipment. 12. The computer-readable non-volatile data carrier of claim 11, wherein the data carrier contains instructions which, when executed by one or more processors, further cause the execution of instructions to: obtain fifth electronic digital data comprising a set of values that reflect previous weather observations for a specific geographic location; calculating one or more predicted values of crop stress indices from a set of values reflecting previous weather observations to create one or more stress indices that take into account the specifics of a geographic location; combining one or more weather indices that take into account the specifics of a geographic area to create one or more combined forecasted weather indices that reflect a specific geographic area from a subset of one or more forecasted weather indices that take into account the specifics of a geographic area; selecting characteristic features from one or more combined predicted weather indices and creating for each geographical area a covariance matrix in computer memory containing characteristic features selected from one or more combined predicted weather indices; calculation of a specific yield of an agricultural crop, taking into account the specifics of a geographic area, based, at least in part, on a covariance matrix that reflects a specific geographic area and a specific potential yield for a specific field. 13. Non-volatile computer-readable data carrier according to claim 12, characterized in that the data carrier contains instructions that, when executed by one or more processors, further cause the execution of instructions for: obtaining information that one or more agricultural crops planted in a certain field; receiving sixth electronic digital data comprising a plurality of values representing received agricultural data points for a specific field at a specific time, wherein the received agricultural data points include one or more of temperature records, soil moisture records, and precipitation records; computing updated crop stress index values from the resulting agricultural data points to generate one or more geographic area-specific weather indices, wherein each of the updated geographic area-specific weather indices includes one or more computed crop stress indices for a specific field during a specific time period; combining one or more updated geo-specific weather indices to create one or more updated combined weather indices representing a specific field at a specific time from a subset of one or more geo-specific updated weather indices ; selecting characteristic features from one or more combined weather indices and creating for a specific field an updated covariance matrix in computer memory containing characteristic features selected from one or more updated combined weather indices; calculating the updated yield of the agricultural crop, taking into account the specifics of the geographical area, based, at least in part, on the updated covariance matrix and the specific potential yield for the specific field. 14. The non-volatile computer-readable storage medium of claim 11, wherein the storage medium contains instructions that, when executed by one or more processors, further cause the execution of instructions for: storing crop relative maturity data comprising a plurality of types of seeds and a set of related values of relative maturity; receiving the proposed planting date for a specific field; determining from the potential yield model of the proposed planting date for a specific field, and from a set of values reflecting actual yield indicators for a specific field, a specific value of relative maturity that will give the maximum potential yield for a specific field; identification in the data of relative ripening of a specific type of seed, which corresponds to a certain value of relative ripening; sending recommendations for a specific type of seed for a proposed planting date and a specific field. 15. The non-volatile computer-readable storage medium of claim 11, wherein the storage medium contains instructions that, when executed by one or more processors, further cause instructions to be executed to: obtain a proposed relative maturation value for a particular field; determining from the potential yield model the proposed value of relative maturity for a specific field, and from the set of values reflecting the actual yield indicators for a specific field, a specific planting date that will give the maximum potential yield for a specific field; sending recommendations for a specific planting date for a suggested relative maturity for a specific field via the network to the field control computing device. 16. The non-volatile computer-readable storage medium of claim 15, wherein the storage medium contains instructions that, when executed by one or more processors, further cause the execution of instructions for: storing crop relative maturity data comprising a plurality of types of seeds and a set of related values of relative maturity; determining that a specific planting date has passed; receiving information that an agricultural crop was not planted on a certain field; determining, from the potential yield model, a plurality of values representing actual yield values for the particular field and one or more current or proposed next planting dates, a particular relative maturity value that differs from the proposed relative maturity value and will yield a maximum potential yield for the particular field; determination in the data of relative ripening for an agricultural crop of a specific type of seed, which corresponds to a certain value of relative ripening; sending recommendations for a specific type of seed for a proposed next planting date and a specific field via the network to the computing device controlling the field operations. 17. The non-volatile computer-readable storage medium of claim 11, wherein the storage medium contains instructions that, when executed by one or more processors, further cause the execution of instructions to: obtain fifth electronic digital data comprising a plurality of values that reflect previous planting dates and previous relative maturity in the plurality of fields; receiving sixth electronic digital data containing a plurality of values that reflect received agricultural events on a plurality of fields; calculating a simulated crop yield for each field of the plurality of fields based at least in part on the fifth electronic digital data, the sixth electronic digital data, and the potential yield model; receiving the seventh electronic digital data containing a plurality of values that reflect the obtained yield of the agricultural crop for each field of the plurality of fields; computing an updated potential yield model based, at least in part, on the simulated crop yield for each field of the plurality of fields and the derived crop yield for each field on the plurality of fields. 18. The non-volatile computer-readable storage medium of claim 11, wherein the storage medium contains instructions that, when executed by one or more processors, further cause the execution of instructions to: generate a potential yield model as a linear function containing a constant parameter multiplied by a set of covariates. 19. Non-volatile computer-readable data carrier according to claim 18, characterized in that the set of covariates includes a planting date parameter, a square of the planting date parameter, a relative ripening parameter, a square of the relative ripening parameter, and a parameter of actual yield values. 20. The non-volatile computer-readable storage medium of claim 11, wherein the storage medium contains instructions that, when executed by one or more processors, further cause the execution of instructions for: determining, based at least in part, one or more maps of relative ripening, one or more maps of planting dates and one or more maps of actual yield indicators, dependence of potential yield on location; generating a model of potential yield as a linear function containing a constant parameter multiplied by a location-dependent set of covariates. - OH nok chor, i04 t . in. s 106 nn u y i Polsvi Zovanna GO " " and data data shi 115 TSI Komaletero | Agricultural 3-cable device with remote control 114 Application controller and sensor: ' 109 Network (1) : ; - ddechuset now EO Communication level z V i i i I - 136 Instructions for modeling the potential rn yield sh-- shen ak 138 Instructions for calculating the index | deer, A 1 and ad and with Kin and y x x yield and and NMZero data " 7 ' | in bShovnshe with TO TeetruUkniy on the production of yield | horse! I34 Presentation level 140 Level of data management and 150 Level of hardware support / virtualization 130 Rural toerporovka intellectual Sochznstovatna system! GO Silsky I with Vi Fig. 1 200 Mobile computer application ! 208! 210 23 | 214 | 216 Instructions (0000 Instructions Instructions | Instructions | 000 Instructions: regarding | regarding regarding | where | regarding ; seeds and application of weather health g productivity of planting nitrogen and field ||. 206 Digital map in the form of a book 205 Instructions for generating honor a NN scripts r. Instructions for general review and warnings What about 802 Instructions for account, field, data acquisition and processing, OPO sahnogovykovykornstannya/.O (a) 220 Cockpit computer application At tt lit ty 1 222 ay Or yayab Collection and 224 230 , Mana - Remote transmission | Warning | Transmission Cabin | og 000 data machine 1 cache claim 232 Observation Cabin.DG 00000 (6) Fig. 2 305 Pre-processing of agronomic data Shy 310 Selection of a subset of a set of agronomic data Cycle of the reverse 1 " vlyasnunu in pnkxyuosnyunnn 315 Evaluation of agronomic data 329 Creation of an agronomic model 325 Saving of an agronomic model Fig. With and and OM 4MPristoy |. Zo sernav', i v she 05 Osmovma zle: i 2zhkraen z I: memory of gathering | y "Uh 428 I E : and ZOV dennyh ! : and Z : and skkkzhnkya : y y and Postechealnya 8apPrasui A X ! interme Shock is g 802 Tire : in y input Gu g Co. : cha N ya : R. Y : ab board ra B poh : : cursor | Ge, mimy m " ddyaketvihy 522: MOP Process of the Brain "Mshkhezhevy luoyvlna pnttntttttnnnnn: interface of the network channel 000000. TT 828 Buzol measure Fig. 4; And Misnezher davyh pa a aa Nitroren oi Grasadka | Practice about | Grukht and horse lochia and ! Dung voksna IOM proguduya FU Khsuilia podi) a okhiho R Kilkistk 153 5 Miss Ha voliv SHO poho Kizekistk. 1) That Myas Z Kn R Chezststyuvno their hands | Kipkisht: LO Oh My M Kilkkti 150 Puv Move Zaspmovamy I x addahkiv Y pdenioyuyuy; : ZtUdzhuvali: Zh leschat M zizetosovano: o x zolatkiv I ih Y dpltnknknnntntnnnk E lpaAAAAAAAt th V. Mk ih ih Z x V s s Vedegevati | accepted vrynyki r releguvatya | accept vedaguvit and accept KIT WHO See TT POV. I I: DK lrlniy MM GI Expressions and: s; 2: from the city; ; , Seri Ber Jeoyut List o Grudo Kiz Lut Ber o Kaiia Trav o Chere Liz Suda b» Epes, Znov and Ai prim p from Kukurui and NY! S gu re : yhya, DOV k - ! Zaddsheak ; Yeyutiv, Ministry of Education! their I Th ta: 5 Bib Z kl i Kukurudyun NY | WHAT TO DO WITH "Breloki, Minnemah in I VALA Trun, Bntsienkh 1 t -o CHINA ote ! ХУ и же ; Ot h Kukuvutsav PNI Sg that 4 Prottttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttttt with Butc, Aioka Terovyh Mizmneini 350 nya GE e Kuherudya: NN: ok YN mn nn nn nt nn nt yaya shk Z MShizmnein, idlineis romelyashnok B Mebrosevi Z Zo kh Z Fe Kukuruza KM 5 , Mr p an 7 eko a iyi madpatok vkrt. Nahukhka : ! Fig. 5 slo Z Mezger dachnh rennia and itrosen | BTirsalka ' Prahtvkhv oyi Grukt U nn yanetnetttteno. Dinecobrations in AAaan on the Kak Criminal Criminal Code Ai corn 1 cockpitus and du dosavyn PL: Duigalosaazha 156 1 Date of posankvn 1346 11 Date of dosadkv 13436 in POT hez MAHK | GENDER OF KZ cats ZNO ONR k't ZNOOYU TO U put ZKYU | , and Sha pf pound U OK Add nevky relvg M accept edit | to try in ekhazuvain, to re-call the TTrURENTS | прайнятн о рам грам гу У Выбозтв выбозтв all MULSUVA reinforced acres will be planted Relative maturity vitssnn роажай к-т прнблнно) date о Ebys, Iowa | y shi t Kukuruva ii: i s. Was, Aiska KUKUVUNIM PiYSaeM 1 180 ZK 0 Kvi tet, Minimata Mukurudivi NI: ik. . . shhe all kntzhzhazhnnzhzhnh di SK dvy KUKUrUDI -- omovm pa ZE kah den. desired | t - sekzhrudzya and 10 in yah x Syai Ot Kuetrulya 061 KUKUrUYNY I ryuisvamya Na tko ZSHHYU Kai - hi, Nova 7 Shahmiktsiv | Щ Os Kukuruma NOI corn - This is Ko Z vit Phymlevn. livaze k R Neirajekt t-ZZ ; about from Kukurul About MU: ZHUZHZHrUDI sn lk 15 shcha KZ Ky: Bert; Nebraska Fig. 6 700 Generating a retrospective map of TV Acquisition 706 Obtaining software Obtaining the values of retrospective relative retrospective values of the actual indicators of the values of maturity for kunitur, called the yield for crops, yields for crops, What is planted on what is planted on what is planted in the plurality of sshЩ - What s ; the field of production of the multiplicity of the density of production fields || multiplicity of oxen throughout. years of multiplicity of years of multiplicity of crayfish 24 Generation to or "708 Generavy of lead or PI Generation of one or more maps of the parentage more than the map of the actual ripening of more than the map of the actual ripening from the retrospective values of the yield indicators obtained from the retrospective values of the values of the planting date values obtained from the values of the ripening of the actual yield indicators and 714 Generation of a potential yield model dependent on planting date and relative maturity based, at least in part, on relative maturity maps, planting date maps, and actual yield maps and i la Obtaining the actual yield values for a rural polar crop planted on a specific field ! and 1715 Calculation by a potential yield model, the exact potential yield for a particular field, based at least in part on the values of the actual historical yield values for the crop planted in the particular field Fig. 7